Authors: Minh-Quan Ho-Le, Duy-Khang Ho, Van-Tu Ninh, Cathal Gurrin, Minh-Triet Tran
Abstract: Lifelogging involves continuously capturing personal data through wearable cameras, providing an egocentric view of daily activities. Lifelog retrieval aims to search and retrieve relevant moments from this data, yet existing methods largely overlook activity-level annotations, which capture temporal relationships and enrich semantic understanding. In this work, we introduce LSC-ADL, an ADL-annotated lifelog dataset derived from the LSC dataset, incorporating Activities of Daily Living (ADLs) as a structured semantic layer. Using a semi-automatic approach featuring the HDBSCAN algorithm for intra-class clustering and human-in-the-loop verification, we generate accurate ADL annotations to enhance retrieval explainability. By integrating action recognition into lifelog retrieval, LSC-ADL bridges a critical gap in existing research, offering a more context-aware representation of daily life. We believe this dataset will advance research in lifelog retrieval, activity recognition, and egocentric vision, ultimately improving the accuracy and interpretability of retrieved content. The ADL annotations can be downloaded at https://bit.ly/lsc-adl-annotations.
Authors: Yuxin Guo, Shuailei Ma, Shijie Ma, Xiaoyi Bao, Chen-Wei Xie, Kecheng Zheng, Tingyu Weng, Siyang Sun, Yun Zheng, Wei Zou
Abstract: Audio is essential for multimodal video understanding. On the one hand, video inherently contains audio, which supplies complementary information to vision. Besides, video large language models (Video-LLMs) can encounter many audio-centric settings. However, existing Video-LLMs and Audio-Visual Large Language Models (AV-LLMs) exhibit deficiencies in exploiting audio information, leading to weak understanding and hallucinations. To solve the issues, we delve into the model architecture and dataset. (1) From the architectural perspective, we propose a fine-grained AV-LLM, namely Dolphin. The concurrent alignment of audio and visual modalities in both temporal and spatial dimensions ensures a comprehensive and accurate understanding of videos. Specifically, we devise an audio-visual multi-scale adapter for multi-scale information aggregation, which achieves spatial alignment. For temporal alignment, we propose audio-visual interleaved merging. (2) From the dataset perspective, we curate an audio-visual caption and instruction-tuning dataset, called AVU. It comprises 5.2 million diverse, open-ended data tuples (video, audio, question, answer) and introduces a novel data partitioning strategy. Extensive experiments show our model not only achieves remarkable performance in audio-visual understanding, but also mitigates potential hallucinations.
Authors: Chao Huang, Susan Liang, Yunlong Tang, Li Ma, Yapeng Tian, Chenliang Xu
Abstract: Diffusion models offer impressive controllability for image tasks, primarily through noise predictions that encode task-specific information and classifier-free guidance enabling adjustable scaling. This scaling mechanism implicitly defines a ``scaling space'' whose potential for fine-grained semantic manipulation remains underexplored. We investigate this space, starting with inversion-based editing where the difference between conditional/unconditional noise predictions carries key semantic information. Our core contribution stems from a Fourier analysis of noise predictions, revealing that its low- and high-frequency components evolve differently throughout diffusion. Based on this insight, we introduce FreSca, a straightforward method that applies guidance scaling independently to different frequency bands in the Fourier domain. FreSca demonstrably enhances existing image editing methods without retraining. Excitingly, its effectiveness extends to image understanding tasks such as depth estimation, yielding quantitative gains across multiple datasets.
Authors: Jaehoon Choi, Dongki Jung, Yonghan Lee, Sungmin Eum, Dinesh Manocha, Heesung Kwon
Abstract: We present UAVTwin, a method for creating digital twins from real-world environments and facilitating data augmentation for training downstream models embedded in unmanned aerial vehicles (UAVs). Specifically, our approach focuses on synthesizing foreground components, such as various human instances in motion within complex scene backgrounds, from UAV perspectives. This is achieved by integrating 3D Gaussian Splatting (3DGS) for reconstructing backgrounds along with controllable synthetic human models that display diverse appearances and actions in multiple poses. To the best of our knowledge, UAVTwin is the first approach for UAV-based perception that is capable of generating high-fidelity digital twins based on 3DGS. The proposed work significantly enhances downstream models through data augmentation for real-world environments with multiple dynamic objects and significant appearance variations-both of which typically introduce artifacts in 3DGS-based modeling. To tackle these challenges, we propose a novel appearance modeling strategy and a mask refinement module to enhance the training of 3D Gaussian Splatting. We demonstrate the high quality of neural rendering by achieving a 1.23 dB improvement in PSNR compared to recent methods. Furthermore, we validate the effectiveness of data augmentation by showing a 2.5% to 13.7% improvement in mAP for the human detection task.
Authors: Shaojin Wu, Mengqi Huang, Wenxu Wu, Yufeng Cheng, Fei Ding, Qian He
Abstract: Although subject-driven generation has been extensively explored in image generation due to its wide applications, it still has challenges in data scalability and subject expansibility. For the first challenge, moving from curating single-subject datasets to multiple-subject ones and scaling them is particularly difficult. For the second, most recent methods center on single-subject generation, making it hard to apply when dealing with multi-subject scenarios. In this study, we propose a highly-consistent data synthesis pipeline to tackle this challenge. This pipeline harnesses the intrinsic in-context generation capabilities of diffusion transformers and generates high-consistency multi-subject paired data. Additionally, we introduce UNO, which consists of progressive cross-modal alignment and universal rotary position embedding. It is a multi-image conditioned subject-to-image model iteratively trained from a text-to-image model. Extensive experiments show that our method can achieve high consistency while ensuring controllability in both single-subject and multi-subject driven generation.
Authors: Xinglong Sun, Barath Lakshmanan, Maying Shen, Shiyi Lan, Jingde Chen, Jose M. Alvarez
Abstract: Current structural pruning methods face two significant limitations: (i) they often limit pruning to finer-grained levels like channels, making aggressive parameter reduction challenging, and (ii) they focus heavily on parameter and FLOP reduction, with existing latency-aware methods frequently relying on simplistic, suboptimal linear models that fail to generalize well to transformers, where multiple interacting dimensions impact latency. In this paper, we address both limitations by introducing Multi-Dimensional Pruning (MDP), a novel paradigm that jointly optimizes across a variety of pruning granularities-including channels, query, key, heads, embeddings, and blocks. MDP employs an advanced latency modeling technique to accurately capture latency variations across all prunable dimensions, achieving an optimal balance between latency and accuracy. By reformulating pruning as a Mixed-Integer Nonlinear Program (MINLP), MDP efficiently identifies the optimal pruned structure across all prunable dimensions while respecting latency constraints. This versatile framework supports both CNNs and transformers. Extensive experiments demonstrate that MDP significantly outperforms previous methods, especially at high pruning ratios. On ImageNet, MDP achieves a 28% speed increase with a +1.4 Top-1 accuracy improvement over prior work like HALP for ResNet50 pruning. Against the latest transformer pruning method, Isomorphic, MDP delivers an additional 37% acceleration with a +0.7 Top-1 accuracy improvement.
Authors: Pei-Chi Chen, Yi Yao, Chan-Feng Hsu, HongXia Xie, Hung-Jen Chen, Hong-Han Shuai, Wen-Huang Cheng
Abstract: Camouflaged image generation is emerging as a solution to data scarcity in camouflaged vision perception, offering a cost-effective alternative to data collection and labeling. Recently, the state-of-the-art approach successfully generates camouflaged images using only foreground objects. However, it faces two critical weaknesses: 1) the background knowledge does not integrate effectively with foreground features, resulting in a lack of foreground-background coherence (e.g., color discrepancy); 2) the generation process does not prioritize the fidelity of foreground objects, which leads to distortion, particularly for small objects. To address these issues, we propose a Foreground-Aware Camouflaged Image Generation (FACIG) model. Specifically, we introduce a Foreground-Aware Feature Integration Module (FAFIM) to strengthen the integration between foreground features and background knowledge. In addition, a Foreground-Aware Denoising Loss is designed to enhance foreground reconstruction supervision. Experiments on various datasets show our method outperforms previous methods in overall camouflaged image quality and foreground fidelity.
Authors: Tae-Young Lee, Sundong Park, Minwoo Jeon, Hyoseok Hwang, Gyeong-Moon Park
Abstract: As concerns regarding privacy in deep learning continue to grow, individuals are increasingly apprehensive about the potential exploitation of their personal knowledge in trained models. Despite several research efforts to address this, they often fail to consider the real-world demand from users for complete knowledge erasure. Furthermore, our investigation reveals that existing methods have a risk of leaking personal knowledge through embedding features. To address these issues, we introduce a novel concept of Knowledge Deletion (KD), an advanced task that considers both concerns, and provides an appropriate metric, named Knowledge Retention score (KR), for assessing knowledge retention in feature space. To achieve this, we propose a novel training-free erasing approach named Erasing Space Concept (ESC), which restricts the important subspace for the forgetting knowledge by eliminating the relevant activations in the feature. In addition, we suggest ESC with Training (ESC-T), which uses a learnable mask to better balance the trade-off between forgetting and preserving knowledge in KD. Our extensive experiments on various datasets and models demonstrate that our proposed methods achieve the fastest and state-of-the-art performance. Notably, our methods are applicable to diverse forgetting scenarios, such as facial domain setting, demonstrating the generalizability of our methods. The code is available at http://github.com/KU-VGI/ESC .
Authors: Hyunho Lee, Wenwen Li
Abstract: Geospatial Artificial Intelligence (GeoAI) for satellite-based flood extent mapping systematically integrates artificial intelligence techniques with satellite data to identify flood events and assess their impacts, for disaster management and spatial decision-making. The primary output often includes flood extent maps, which delineate the affected areas, along with additional analytical outputs such as uncertainty estimation and change detection.
Authors: Zhipu Cui, Andong Tian, Zhi Ying, Jialiang Lu
Abstract: Personalized image generation allows users to preserve styles or subjects of a provided small set of images for further image generation. With the advancement in large text-to-image models, many techniques have been developed to efficiently fine-tune those models for personalization, such as Low Rank Adaptation (LoRA). However, LoRA-based methods often face the challenge of adjusting the rank parameter to achieve satisfactory results. To address this challenge, AutoComponent-LoRA (AC-LoRA) is proposed, which is able to automatically separate the signal component and noise component of the LoRA matrices for fast and efficient personalized artistic style image generation. This method is based on Singular Value Decomposition (SVD) and dynamic heuristics to update the hyperparameters during training. Superior performance over existing methods in overcoming model underfitting or overfitting problems is demonstrated. The results were validated using FID, CLIP, DINO, and ImageReward, achieving an average of 9% improvement.
Authors: Xu Cao, Pranav Virupaksha, Wenqi Jia, Bolin Lai, Fiona Ryan, Sangmin Lee, James M. Rehg
Abstract: Previous research in human gesture recognition has largely overlooked multi-person interactions, which are crucial for understanding the social context of naturally occurring gestures. This limitation in existing datasets presents a significant challenge in aligning human gestures with other modalities like language and speech. To address this issue, we introduce SocialGesture, the first large-scale dataset specifically designed for multi-person gesture analysis. SocialGesture features a diverse range of natural scenarios and supports multiple gesture analysis tasks, including video-based recognition and temporal localization, providing a valuable resource for advancing the study of gesture during complex social interactions. Furthermore, we propose a novel visual question answering (VQA) task to benchmark vision language models'(VLMs) performance on social gesture understanding. Our findings highlight several limitations of current gesture recognition models, offering insights into future directions for improvement in this field. SocialGesture is available at huggingface.co/datasets/IrohXu/SocialGesture.
Authors: Jinhui Ye, Zihan Wang, Haosen Sun, Keshigeyan Chandrasegaran, Zane Durante, Cristobal Eyzaguirre, Yonatan Bisk, Juan Carlos Niebles, Ehsan Adeli, Li Fei-Fei, Jiajun Wu, Manling Li
Abstract: Efficient understanding of long-form videos remains a significant challenge in computer vision. In this work, we revisit temporal search paradigms for long-form video understanding, studying a fundamental issue pertaining to all state-of-the-art (SOTA) long-context vision-language models (VLMs). In particular, our contributions are two-fold: First, we formulate temporal search as a Long Video Haystack problem, i.e., finding a minimal set of relevant frames (typically one to five) among tens of thousands of frames from real-world long videos given specific queries. To validate our formulation, we create LV-Haystack, the first benchmark containing 3,874 human-annotated instances with fine-grained evaluation metrics for assessing keyframe search quality and computational efficiency. Experimental results on LV-Haystack highlight a significant research gap in temporal search capabilities, with SOTA keyframe selection methods achieving only 2.1% temporal F1 score on the LVBench subset. Next, inspired by visual search in images, we re-think temporal searching and propose a lightweight keyframe searching framework, T*, which casts the expensive temporal search as a spatial search problem. T* leverages superior visual localization capabilities typically used in images and introduces an adaptive zooming-in mechanism that operates across both temporal and spatial dimensions. Our extensive experiments show that when integrated with existing methods, T* significantly improves SOTA long-form video understanding performance. Specifically, under an inference budget of 32 frames, T* improves GPT-4o's performance from 50.5% to 53.1% and LLaVA-OneVision-72B's performance from 56.5% to 62.4% on LongVideoBench XL subset. Our PyTorch code, benchmark dataset and models are included in the Supplementary material.
Authors: Chaojun Ni, Xiaofeng Wang, Zheng Zhu, Weijie Wang, Haoyun Li, Guosheng Zhao, Jie Li, Wenkang Qin, Guan Huang, Wenjun Mei
Abstract: Interactive 3D generation is gaining momentum and capturing extensive attention for its potential to create immersive virtual experiences. However, a critical challenge in current 3D generation technologies lies in achieving real-time interactivity. To address this issue, we introduce WonderTurbo, the first real-time interactive 3D scene generation framework capable of generating novel perspectives of 3D scenes within 0.72 seconds. Specifically, WonderTurbo accelerates both geometric and appearance modeling in 3D scene generation. In terms of geometry, we propose StepSplat, an innovative method that constructs efficient 3D geometric representations through dynamic updates, each taking only 0.26 seconds. Additionally, we design QuickDepth, a lightweight depth completion module that provides consistent depth input for StepSplat, further enhancing geometric accuracy. For appearance modeling, we develop FastPaint, a 2-steps diffusion model tailored for instant inpainting, which focuses on maintaining spatial appearance consistency. Experimental results demonstrate that WonderTurbo achieves a remarkable 15X speedup compared to baseline methods, while preserving excellent spatial consistency and delivering high-quality output.
Authors: Wenzhuo Liu, Wenshuo Wang, Yicheng Qiao, Qiannan Guo, Jiayin Zhu, Pengfei Li, Zilong Chen, Huiming Yang, Zhiwei Li, Lening Wang, Tiao Tan, Huaping Liu
Abstract: Advanced driver assistance systems require a comprehensive understanding of the driver's mental/physical state and traffic context but existing works often neglect the potential benefits of joint learning between these tasks. This paper proposes MMTL-UniAD, a unified multi-modal multi-task learning framework that simultaneously recognizes driver behavior (e.g., looking around, talking), driver emotion (e.g., anxiety, happiness), vehicle behavior (e.g., parking, turning), and traffic context (e.g., traffic jam, traffic smooth). A key challenge is avoiding negative transfer between tasks, which can impair learning performance. To address this, we introduce two key components into the framework: one is the multi-axis region attention network to extract global context-sensitive features, and the other is the dual-branch multimodal embedding to learn multimodal embeddings from both task-shared and task-specific features. The former uses a multi-attention mechanism to extract task-relevant features, mitigating negative transfer caused by task-unrelated features. The latter employs a dual-branch structure to adaptively adjust task-shared and task-specific parameters, enhancing cross-task knowledge transfer while reducing task conflicts. We assess MMTL-UniAD on the AIDE dataset, using a series of ablation studies, and show that it outperforms state-of-the-art methods across all four tasks. The code is available on https://github.com/Wenzhuo-Liu/MMTL-UniAD.
Authors: Samuel Sze, Daniele De Martini, Lars Kunze
Abstract: Developing 3D semantic occupancy prediction models often relies on dense 3D annotations for supervised learning, a process that is both labor and resource-intensive, underscoring the need for label-efficient or even label-free approaches. To address this, we introduce MinkOcc, a multi-modal 3D semantic occupancy prediction framework for cameras and LiDARs that proposes a two-step semi-supervised training procedure. Here, a small dataset of explicitly 3D annotations warm-starts the training process; then, the supervision is continued by simpler-to-annotate accumulated LiDAR sweeps and images -- semantically labelled through vision foundational models. MinkOcc effectively utilizes these sensor-rich supervisory cues and reduces reliance on manual labeling by 90\% while maintaining competitive accuracy. In addition, the proposed model incorporates information from LiDAR and camera data through early fusion and leverages sparse convolution networks for real-time prediction. With its efficiency in both supervision and computation, we aim to extend MinkOcc beyond curated datasets, enabling broader real-world deployment of 3D semantic occupancy prediction in autonomous driving.
Authors: Shaocong Long, Qianyu Zhou, Xiangtai Li, Chenhao Ying, Yunhai Tong, Lizhuang Ma, Yuan Luo, Dacheng Tao
Abstract: Domain generalization (DG) aims to improve the generalizability of computer vision models toward distribution shifts. The mainstream DG methods focus on learning domain invariance, however, such methods overlook the potential inherent in domain-specific information. While the prevailing practice of discriminative linear classifier has been tailored to domain-invariant features, it struggles when confronted with diverse domain-specific information, e.g., intra-class shifts, that exhibits multi-modality. To address these issues, we explore the theoretical implications of relying on domain invariance, revealing the crucial role of domain-specific information in mitigating the target risk for DG. Drawing from these insights, we propose Generative Classifier-driven Domain Generalization (GCDG), introducing a generative paradigm for the DG classifier based on Gaussian Mixture Models (GMMs) for each class across domains. GCDG consists of three key modules: Heterogeneity Learning Classifier~(HLC), Spurious Correlation Blocking~(SCB), and Diverse Component Balancing~(DCB). Concretely, HLC attempts to model the feature distributions and thereby capture valuable domain-specific information via GMMs. SCB identifies the neural units containing spurious correlations and perturbs them, mitigating the risk of HLC learning spurious patterns. Meanwhile, DCB ensures a balanced contribution of components in HLC, preventing the underestimation or neglect of critical components. In this way, GCDG excels in capturing the nuances of domain-specific information characterized by diverse distributions. GCDG demonstrates the potential to reduce the target risk and encourage flat minima, improving the generalizability. Extensive experiments show GCDG's comparable performance on five DG benchmarks and one face anti-spoofing dataset, seamlessly integrating into existing DG methods with consistent improvements.
Authors: Amit Rand, Hadi Ibrahim
Abstract: Medical imaging, particularly X-ray analysis, often involves detecting multiple conditions simultaneously within a single scan, making multi-label classification crucial for real-world clinical applications. We present the Medical X-ray Attention (MXA) block, a novel attention mechanism tailored specifically to address the unique challenges of X-ray abnormality detection. The MXA block enhances traditional Multi-Head Self Attention (MHSA) by integrating a specialized module that efficiently captures both detailed local information and broader global context. To the best of our knowledge, this is the first work to propose a task-specific attention mechanism for diagnosing chest X-rays, as well as to attempt multi-label classification using an Efficient Vision Transformer (EfficientViT). By embedding the MXA block within the EfficientViT architecture and employing knowledge distillation, our proposed model significantly improves performance on the CheXpert dataset, a widely used benchmark for multi-label chest X-ray abnormality detection. Our approach achieves an area under the curve (AUC) of 0.85, an absolute improvement of 0.19 compared to our baseline model's AUC of 0.66, corresponding to a substantial approximate 233% relative improvement over random guessing (AUC = 0.5).
Authors: Trung Thanh Nguyen, Yasutomo Kawanishi, Vijay John, Takahiro Komamizu, Ichiro Ide
Abstract: Action recognition from multi-modal and multi-view observations holds significant potential for applications in surveillance, robotics, and smart environments. However, existing methods often fall short of addressing real-world challenges such as diverse environmental conditions, strict sensor synchronization, and the need for fine-grained annotations. In this study, we propose the Multi-modal Multi-view Transformer-based Sensor Fusion (MultiTSF). The proposed method leverages a Transformer-based to dynamically model inter-view relationships and capture temporal dependencies across multiple views. Additionally, we introduce a Human Detection Module to generate pseudo-ground-truth labels, enabling the model to prioritize frames containing human activity and enhance spatial feature learning. Comprehensive experiments conducted on our in-house MultiSensor-Home dataset and the existing MM-Office dataset demonstrate that MultiTSF outperforms state-of-the-art methods in both video sequence-level and frame-level action recognition settings.
Authors: Xiaolong Sun, Le Wang, Sanping Zhou, Liushuai Shi, Kun Xia, Mengnan Liu, Yabing Wang, Gang Hua
Abstract: Video temporal grounding is a critical video understanding task, which aims to localize moments relevant to a language description. The challenge of this task lies in distinguishing relevant and irrelevant moments. Previous methods focused on learning continuous features exhibit weak differentiation between foreground and background features. In this paper, we propose a novel Moment-Quantization based Video Temporal Grounding method (MQVTG), which quantizes the input video into various discrete vectors to enhance the discrimination between relevant and irrelevant moments. Specifically, MQVTG maintains a learnable moment codebook, where each video moment matches a codeword. Considering the visual diversity, i.e., various visual expressions for the same moment, MQVTG treats moment-codeword matching as a clustering process without using discrete vectors, avoiding the loss of useful information from direct hard quantization. Additionally, we employ effective prior-initialization and joint-projection strategies to enhance the maintained moment codebook. With its simple implementation, the proposed method can be integrated into existing temporal grounding models as a plug-and-play component. Extensive experiments on six popular benchmarks demonstrate the effectiveness and generalizability of MQVTG, significantly outperforming state-of-the-art methods. Further qualitative analysis shows that our method effectively groups relevant features and separates irrelevant ones, aligning with our goal of enhancing discrimination.
Authors: Trung Thanh Nguyen, Yasutomo Kawanishi, Vijay John, Takahiro Komamizu, Ichiro Ide
Abstract: Multi-modal multi-view action recognition is a rapidly growing field in computer vision, offering significant potential for applications in surveillance. However, current datasets often fail to address real-world challenges such as wide-area environmental conditions, asynchronous data streams, and the lack of frame-level annotations. Furthermore, existing methods face difficulties in effectively modeling inter-view relationships and enhancing spatial feature learning. In this study, we propose the Multi-modal Multi-view Transformer-based Sensor Fusion (MultiTSF) method and introduce the MultiSensor-Home dataset, a novel benchmark designed for comprehensive action recognition in home environments. The MultiSensor-Home dataset features untrimmed videos captured by distributed sensors, providing high-resolution RGB and audio data along with detailed multi-view frame-level action labels. The proposed MultiTSF method leverages a Transformer-based fusion mechanism to dynamically model inter-view relationships. Furthermore, the method also integrates a external human detection module to enhance spatial feature learning. Experiments on MultiSensor-Home and MM-Office datasets demonstrate the superiority of MultiTSF over the state-of-the-art methods. The quantitative and qualitative results highlight the effectiveness of the proposed method in advancing real-world multi-modal multi-view action recognition.
Authors: Xiaoda Yang, Jiayang Xu, Kaixuan Luan, Xinyu Zhan, Hongshun Qiu, Shijun Shi, Hao Li, Shuai Yang, Li Zhang, Checheng Yu, Cewu Lu, Lixin Yang
Abstract: Camera control, which achieves diverse visual effects by changing camera position and pose, has attracted widespread attention. However, existing methods face challenges such as complex interaction and limited control capabilities. To address these issues, we present OmniCam, a unified multimodal camera control framework. Leveraging large language models and video diffusion models, OmniCam generates spatio-temporally consistent videos. It supports various combinations of input modalities: the user can provide text or video with expected trajectory as camera path guidance, and image or video as content reference, enabling precise control over camera motion. To facilitate the training of OmniCam, we introduce the OmniTr dataset, which contains a large collection of high-quality long-sequence trajectories, videos, and corresponding descriptions. Experimental results demonstrate that our model achieves state-of-the-art performance in high-quality camera-controlled video generation across various metrics.
Authors: Yuan Zhou, Shilong Jin, Litao Hua, Wanjun Lv, Haoran Duan, Jungong Han
Abstract: Recent advances in zero-shot text-to-3D generation have revolutionized 3D content creation by enabling direct synthesis from textual descriptions. While state-of-the-art methods leverage 3D Gaussian Splatting with score distillation to enhance multi-view rendering through pre-trained text-to-image (T2I) models, they suffer from inherent view biases in T2I priors. These biases lead to inconsistent 3D generation, particularly manifesting as the multi-face Janus problem, where objects exhibit conflicting features across views. To address this fundamental challenge, we propose ConsDreamer, a novel framework that mitigates view bias by refining both the conditional and unconditional terms in the score distillation process: (1) a View Disentanglement Module (VDM) that eliminates viewpoint biases in conditional prompts by decoupling irrelevant view components and injecting precise camera parameters; and (2) a similarity-based partial order loss that enforces geometric consistency in the unconditional term by aligning cosine similarities with azimuth relationships. Extensive experiments demonstrate that ConsDreamer effectively mitigates the multi-face Janus problem in text-to-3D generation, outperforming existing methods in both visual quality and consistency.
Authors: Samuel Clarke, Suzannah Wistreich, Yanjie Ze, Jiajun Wu
Abstract: Understanding objects through multiple sensory modalities is fundamental to human perception, enabling cross-sensory integration and richer comprehension. For AI and robotic systems to replicate this ability, access to diverse, high-quality multi-sensory data is critical. Existing datasets are often limited by their focus on controlled environments, simulated objects, or restricted modality pairings. We introduce X-Capture, an open-source, portable, and cost-effective device for real-world multi-sensory data collection, capable of capturing correlated RGBD images, tactile readings, and impact audio. With a build cost under $1,000, X-Capture democratizes the creation of multi-sensory datasets, requiring only consumer-grade tools for assembly. Using X-Capture, we curate a sample dataset of 3,000 total points on 500 everyday objects from diverse, real-world environments, offering both richness and variety. Our experiments demonstrate the value of both the quantity and the sensory breadth of our data for both pretraining and fine-tuning multi-modal representations for object-centric tasks such as cross-sensory retrieval and reconstruction. X-Capture lays the groundwork for advancing human-like sensory representations in AI, emphasizing scalability, accessibility, and real-world applicability.
Authors: Congpei Qiu, Yanhao Wu, Wei Ke, Xiuxiu Bai, Tong Zhang
Abstract: Contrastive Language-Image Pre-training (CLIP) excels in global alignment with language but exhibits limited sensitivity to spatial information, leading to strong performance in zero-shot classification tasks but underperformance in tasks requiring precise spatial understanding. Recent approaches have introduced Region-Language Alignment (RLA) to enhance CLIP's performance in dense multimodal tasks by aligning regional visual representations with corresponding text inputs. However, we find that CLIP ViTs fine-tuned with RLA suffer from notable loss in spatial awareness, which is crucial for dense prediction tasks. To address this, we propose the Spatial Correlation Distillation (SCD) framework, which preserves CLIP's inherent spatial structure and mitigates the above degradation. To further enhance spatial correlations, we introduce a lightweight Refiner that extracts refined correlations directly from CLIP before feeding them into SCD, based on an intriguing finding that CLIP naturally captures high-quality dense features. Together, these components form a robust distillation framework that enables CLIP ViTs to integrate both visual-language and visual-centric improvements, achieving state-of-the-art results across various open-vocabulary dense prediction benchmarks.
Authors: Seif Mzoughi, Mohamed Elshafeia, Foutse Khomh
Abstract: Image segmentation is critical for applications such as medical imaging, augmented reality, and video surveillance. However, segmentation models often lack robustness, making them vulnerable to adversarial perturbations from subtle image distortions. In this work, we propose SegRMT, a metamorphic testing approach that leverages genetic algorithms (GA) to optimize sequences of spatial and spectral transformations while preserving image fidelity via a predefined PSNR threshold. Using the Cityscapes dataset, our method generates adversarial examples that effectively challenge the DeepLabV3 segmentation model. Our experiments show that SegRMT reduces DeepLabV3's mean Intersection over Union (mIoU) to 6.4%, outperforming other adversarial baselines that decrease mIoU to between 8.5% and 21.7%. Furthermore, when used for adversarial training, SegRMT boosts model performance, achieving mIoU improvements up to 73% on dedicated adversarial datasets and increasing cross-adversarial mIoU to 53.8%, compared to only 2%-10% for other methods. These findings demonstrate that SegRMT not only simulates realistic image distortions but also enhances the robustness of segmentation models, making it a valuable tool for ensuring reliable performance in safety-critical applications.
Authors: Ming-Jia Yang, Yu-Xiao Guo, Yang Liu, Bin Zhou, Xin Tong
Abstract: Generating realistic, room-level indoor scenes with semantically plausible and detailed appearances from in-the-wild images is crucial for various applications in VR, AR, and robotics. The success of NeRF-based generative methods indicates a promising direction to address this challenge. However, unlike their success at the object level, existing scene-level generative methods require additional information, such as multiple views, depth images, or semantic guidance, rather than relying solely on RGB images. This is because NeRF-based methods necessitate prior knowledge of camera poses, which is challenging to approximate for indoor scenes due to the complexity of defining alignment and the difficulty of globally estimating poses from a single image, given the unseen parts behind the camera. To address this challenge, we redefine global poses within the framework of Local-Pose-Alignment (LPA) -- an anchor-based multi-local-coordinate system that uses a selected number of anchors as the roots of these coordinates. Building on this foundation, we introduce LPA-GAN, a novel NeRF-based generative approach that incorporates specific modifications to estimate the priors of camera poses under LPA. It also co-optimizes the pose predictor and scene generation processes. Our ablation study and comparisons with straightforward extensions of NeRF-based object generative methods demonstrate the effectiveness of our approach. Furthermore, visual comparisons with other techniques reveal that our method achieves superior view-to-view consistency and semantic normality.
Authors: Masakazu Yoshimura, Junji Otsuka, Radu Berdan, Takeshi Ohashi
Abstract: DNN-based methods have been successful in Image Signal Processor (ISP) and image enhancement (IE) tasks. However, the cost of creating training data for these tasks is considerably higher than for other tasks, making it difficult to prepare large-scale datasets. Also, creating personalized ISP and IE with minimal training data can lead to new value streams since preferred image quality varies depending on the person and use case. While semi-supervised learning could be a potential solution in such cases, it has rarely been utilized for these tasks. In this paper, we realize semi-supervised learning for ISP and IE leveraging a RAW image reconstruction (sRGB-to-RAW) method. Although existing sRGB-to-RAW methods can generate pseudo-RAW image datasets that improve the accuracy of RAW-based high-level computer vision tasks such as object detection, their quality is not sufficient for ISP and IE tasks that require precise image quality definition. Therefore, we also propose a sRGB-to-RAW method that can improve the image quality of these tasks. The proposed semi-supervised learning with the proposed sRGB-to-RAW method successfully improves the image quality of various models on various datasets.
Authors: Chengxi Zeng, Yuxuan Jiang, Fan Zhang, Alberto Gambaruto, Tilo Burghardt
Abstract: The deployment of foundation models for medical imaging has demonstrated considerable success. However, their training overheads associated with downstream tasks remain substantial due to the size of the image encoders employed, and the inference complexity is also significantly high. Although lightweight variants have been obtained for these foundation models, their performance is constrained by their limited model capacity and suboptimal training strategies. In order to achieve an improved tradeoff between complexity and performance, we propose a new framework to improve the performance of low complexity models via knowledge distillation from multiple large medical foundation models (e.g., MedSAM, RAD-DINO, MedCLIP), each specializing in different vision tasks, with the goal to effectively bridge the performance gap for medical image segmentation tasks. The agglomerated model demonstrates superior generalization across 12 segmentation tasks, whereas specialized models require explicit training for each task. Our approach achieved an average performance gain of 2\% in Dice coefficient compared to simple distillation.
Authors: Janghyun Kim, Minseong Kweon, Jinsun Park, Ukcheol Shin
Abstract: Depth completion, which estimates dense depth from sparse LiDAR and RGB images, has demonstrated outstanding performance in well-lit conditions. However, due to the limitations of RGB sensors, existing methods often struggle to achieve reliable performance in harsh environments, such as heavy rain and low-light conditions. Furthermore, we observe that ground truth depth maps often suffer from large missing measurements in adverse weather conditions such as heavy rain, leading to insufficient supervision. In contrast, thermal cameras are known for providing clear and reliable visibility in such conditions, yet research on thermal-LiDAR depth completion remains underexplored. Moreover, the characteristics of thermal images, such as blurriness, low contrast, and noise, bring unclear depth boundary problems. To address these challenges, we first evaluate the feasibility and robustness of thermal-LiDAR depth completion across diverse lighting (eg., well-lit, low-light), weather (eg., clear-sky, rainy), and environment (eg., indoor, outdoor) conditions, by conducting extensive benchmarks on the MS$^2$ and ViViD datasets. In addition, we propose a framework that utilizes COntrastive learning and Pseudo-Supervision (COPS) to enhance depth boundary clarity and improve completion accuracy by leveraging a depth foundation model in two key ways. First, COPS enforces a depth-aware contrastive loss between different depth points by mining positive and negative samples using a monocular depth foundation model to sharpen depth boundaries. Second, it mitigates the issue of incomplete supervision from ground truth depth maps by leveraging foundation model predictions as dense depth priors. We also provide in-depth analyses of the key challenges in thermal-LiDAR depth completion to aid in understanding the task and encourage future research.
Authors: Haodian Wang, Long Peng, Yuejin Sun, Zengyu Wan, Yang Wang, Yang Cao
Abstract: Due to the wide dynamic range in real low-light scenes, there will be large differences in the degree of contrast degradation and detail blurring of captured images, making it difficult for existing end-to-end methods to enhance low-light images to normal exposure. To address the above issue, we decompose low-light image enhancement into a recursive enhancement task and propose a brightness-perceiving-based recursive enhancement framework for high dynamic range low-light image enhancement. Specifically, our recursive enhancement framework consists of two parallel sub-networks: Adaptive Contrast and Texture enhancement network (ACT-Net) and Brightness Perception network (BP-Net). The ACT-Net is proposed to adaptively enhance image contrast and details under the guidance of the brightness adjustment branch and gradient adjustment branch, which are proposed to perceive the degradation degree of contrast and details in low-light images. To adaptively enhance images captured under different brightness levels, BP-Net is proposed to control the recursive enhancement times of ACT-Net by exploring the image brightness distribution properties. Finally, in order to coordinate ACT-Net and BP-Net, we design a novel unsupervised training strategy to facilitate the training procedure. To further validate the effectiveness of the proposed method, we construct a new dataset with a broader brightness distribution by mixing three low-light datasets. Compared with eleven existing representative methods, the proposed method achieves new SOTA performance on six reference and no reference metrics. Specifically, the proposed method improves the PSNR by 0.9 dB compared to the existing SOTA method.
Authors: Kim Sung-Bin, Jeongsoo Choi, Puyuan Peng, Joon Son Chung, Tae-Hyun Oh, David Harwath
Abstract: We present VoiceCraft-Dub, a novel approach for automated video dubbing that synthesizes high-quality speech from text and facial cues. This task has broad applications in filmmaking, multimedia creation, and assisting voice-impaired individuals. Building on the success of Neural Codec Language Models (NCLMs) for speech synthesis, our method extends their capabilities by incorporating video features, ensuring that synthesized speech is time-synchronized and expressively aligned with facial movements while preserving natural prosody. To inject visual cues, we design adapters to align facial features with the NCLM token space and introduce audio-visual fusion layers to merge audio-visual information within the NCLM framework. Additionally, we curate CelebV-Dub, a new dataset of expressive, real-world videos specifically designed for automated video dubbing. Extensive experiments show that our model achieves high-quality, intelligible, and natural speech synthesis with accurate lip synchronization, outperforming existing methods in human perception and performing favorably in objective evaluations. We also adapt VoiceCraft-Dub for the video-to-speech task, demonstrating its versatility for various applications.
Authors: Laibin Chang, Yunke Wang, JiaXing Huang, Longxiang Deng, Bo Du, Chang Xu
Abstract: Marine Saliency Segmentation (MSS) plays a pivotal role in various vision-based marine exploration tasks. However, existing marine segmentation techniques face the dilemma of object mislocalization and imprecise boundaries due to the complex underwater environment. Meanwhile, despite the impressive performance of diffusion models in visual segmentation, there remains potential to further leverage contextual semantics to enhance feature learning of region-level salient objects, thereby improving segmentation outcomes. Building on this insight, we propose DiffMSS, a novel marine saliency segmenter based on the diffusion model, which utilizes semantic knowledge distillation to guide the segmentation of marine salient objects. Specifically, we design a region-word similarity matching mechanism to identify salient terms at the word level from the text descriptions. These high-level semantic features guide the conditional feature learning network in generating salient and accurate diffusion conditions with semantic knowledge distillation. To further refine the segmentation of fine-grained structures in unique marine organisms, we develop the dedicated consensus deterministic sampling to suppress overconfident missegmentations. Comprehensive experiments demonstrate the superior performance of DiffMSS over state-of-the-art methods in both quantitative and qualitative evaluations.
Authors: Boseung Jeong, Jicheol Park, Sungyeon Kim, Suha Kwak
Abstract: Video-text retrieval, the task of retrieving videos based on a textual query or vice versa, is of paramount importance for video understanding and multimodal information retrieval. Recent methods in this area rely primarily on visual and textual features and often ignore audio, although it helps enhance overall comprehension of video content. Moreover, traditional models that incorporate audio blindly utilize the audio input regardless of whether it is useful or not, resulting in suboptimal video representation. To address these limitations, we propose a novel video-text retrieval framework, Audio-guided VIdeo representation learning with GATEd attention (AVIGATE), that effectively leverages audio cues through a gated attention mechanism that selectively filters out uninformative audio signals. In addition, we propose an adaptive margin-based contrastive loss to deal with the inherently unclear positive-negative relationship between video and text, which facilitates learning better video-text alignment. Our extensive experiments demonstrate that AVIGATE achieves state-of-the-art performance on all the public benchmarks.
Authors: Peifu Liu, Huiyan Bai, Tingfa Xu, Jihui Wang, Huan Chen, Jianan Li
Abstract: The objective of hyperspectral remote sensing image salient object detection (HRSI-SOD) is to identify objects or regions that exhibit distinct spectrum contrasts with the background. This area holds significant promise for practical applications; however, progress has been limited by a notable scarcity of dedicated datasets and methodologies. To bridge this gap and stimulate further research, we introduce the first HRSI-SOD dataset, termed HRSSD, which includes 704 hyperspectral images and 5327 pixel-level annotated salient objects. The HRSSD dataset poses substantial challenges for salient object detection algorithms due to large scale variation, diverse foreground-background relations, and multi-salient objects. Additionally, we propose an innovative and efficient baseline model for HRSI-SOD, termed the Deep Spectral Saliency Network (DSSN). The core of DSSN is the Cross-level Saliency Assessment Block, which performs pixel-wise attention and evaluates the contributions of multi-scale similarity maps at each spatial location, effectively reducing erroneous responses in cluttered regions and emphasizes salient regions across scales. Additionally, the High-resolution Fusion Module combines bottom-up fusion strategy and learned spatial upsampling to leverage the strengths of multi-scale saliency maps, ensuring accurate localization of small objects. Experiments on the HRSSD dataset robustly validate the superiority of DSSN, underscoring the critical need for specialized datasets and methodologies in this domain. Further evaluations on the HSOD-BIT and HS-SOD datasets demonstrate the generalizability of the proposed method. The dataset and source code are publicly available at https://github.com/laprf/HRSSD.
Authors: Lili Liang, Guanglu Sun
Abstract: Video Question Answering (VideoQA) is an important research direction in the field of artificial intelligence, enabling machines to understand video content and perform reasoning and answering based on natural language questions. Although methods based on static relationship reasoning have made certain progress, there are still deficiencies in the accuracy of static relationship recognition and representation, and they have not fully utilized the static relationship information in videos for in-depth reasoning and analysis. Therefore, this paper proposes a reasoning method for intra-type and inter-type message passing based on static relationships. This method constructs a dual graph for intra-type message passing reasoning and builds a heterogeneous graph based on static relationships for inter-type message passing reasoning. The intra-type message passing reasoning model captures the neighborhood information of targets and relationships related to the question in the dual graph, updating the dual graph to obtain intra-type clues for answering the question. The inter-type message passing reasoning model captures the neighborhood information of targets and relationships from different categories related to the question in the heterogeneous graph, updating the heterogeneous graph to obtain inter-type clues for answering the question. Finally, the answers are inferred by combining the intra-type and inter-type clues based on static relationships. Experimental results on the ANetQA and Next-QA datasets demonstrate the effectiveness of this method.
Authors: Zhongjian Wang, Peng Zhang, Jinwei Qi, Guangyuan Wang Sheng Xu, Bang Zhang, Liefeng Bo
Abstract: Recent years have witnessed remarkable advances in talking head generation, owing to its potential to revolutionize the human-AI interaction from text interfaces into realistic video chats. However, research on text-driven talking heads remains underexplored, with existing methods predominantly adopting a cascaded pipeline that combines TTS systems with audio-driven talking head models. This conventional pipeline not only introduces system complexity and latency overhead but also fundamentally suffers from asynchronous audiovisual output and stylistic discrepancies between generated speech and visual expressions. To address these limitations, we introduce OmniTalker, an end-to-end unified framework that simultaneously generates synchronized speech and talking head videos from text and reference video in real-time zero-shot scenarios, while preserving both speech style and facial styles. The framework employs a dual-branch diffusion transformer architecture: the audio branch synthesizes mel-spectrograms from text, while the visual branch predicts fine-grained head poses and facial dynamics. To bridge modalities, we introduce a novel audio-visual fusion module that integrates cross-modal information to ensure temporal synchronization and stylistic coherence between audio and visual outputs. Furthermore, our in-context reference learning module effectively captures both speech and facial style characteristics from a single reference video without introducing an extra style extracting module. To the best of our knowledge, OmniTalker presents the first unified framework that jointly models speech style and facial style in a zero-shot setting, achieving real-time inference speed of 25 FPS. Extensive experiments demonstrate that our method surpasses existing approaches in generation quality, particularly excelling in style preservation and audio-video synchronization.
Authors: Zhengcong Fei, Debang Li, Di Qiu, Jiahua Wang, Yikun Dou, Rui Wang, Jingtao Xu, Mingyuan Fan, Guibin Chen, Yang Li, Yahui Zhou
Abstract: This paper presents SkyReels-A2, a controllable video generation framework capable of assembling arbitrary visual elements (e.g., characters, objects, backgrounds) into synthesized videos based on textual prompts while maintaining strict consistency with reference images for each element. We term this task elements-to-video (E2V), whose primary challenges lie in preserving the fidelity of each reference element, ensuring coherent composition of the scene, and achieving natural outputs. To address these, we first design a comprehensive data pipeline to construct prompt-reference-video triplets for model training. Next, we propose a novel image-text joint embedding model to inject multi-element representations into the generative process, balancing element-specific consistency with global coherence and text alignment. We also optimize the inference pipeline for both speed and output stability. Moreover, we introduce a carefully curated benchmark for systematic evaluation, i.e, A2 Bench. Experiments demonstrate that our framework can generate diverse, high-quality videos with precise element control. SkyReels-A2 is the first open-source commercial grade model for the generation of E2V, performing favorably against advanced closed-source commercial models. We anticipate SkyReels-A2 will advance creative applications such as drama and virtual e-commerce, pushing the boundaries of controllable video generation.
Authors: Renwu Li, Wenjing Ke, Dong Li, Lu Tian, Emad Barsoum
Abstract: We present MonoGS++, a novel fast and accurate Simultaneous Localization and Mapping (SLAM) method that leverages 3D Gaussian representations and operates solely on RGB inputs. While previous 3D Gaussian Splatting (GS)-based methods largely depended on depth sensors, our approach reduces the hardware dependency and only requires RGB input, leveraging online visual odometry (VO) to generate sparse point clouds in real-time. To reduce redundancy and enhance the quality of 3D scene reconstruction, we implemented a series of methodological enhancements in 3D Gaussian mapping. Firstly, we introduced dynamic 3D Gaussian insertion to avoid adding redundant Gaussians in previously well-reconstructed areas. Secondly, we introduced clarity-enhancing Gaussian densification module and planar regularization to handle texture-less areas and flat surfaces better. We achieved precise camera tracking results both on the synthetic Replica and real-world TUM-RGBD datasets, comparable to those of the state-of-the-art. Additionally, our method realized a significant 5.57x improvement in frames per second (fps) over the previous state-of-the-art, MonoGS.
Authors: Hao Wang, Shuo Zhang, Biao Leng
Abstract: The computer vision community has witnessed an extensive exploration of vision transformers in the past two years. Drawing inspiration from traditional schemes, numerous works focus on introducing vision-specific inductive biases. However, the implicit modeling of permutation invariance and fully-connected interaction with individual tokens disrupts the regional context and spatial topology, further hindering higher-order modeling. This deviates from the principle of perceptual organization that emphasizes the local groups and overall topology of visual elements. Thus, we introduce the concept of hypergraph for perceptual exploration. Specifically, we propose a topology-aware vision transformer called HyperGraph Transformer (HGFormer). Firstly, we present a Center Sampling K-Nearest Neighbors (CS-KNN) algorithm for semantic guidance during hypergraph construction. Secondly, we present a topology-aware HyperGraph Attention (HGA) mechanism that integrates hypergraph topology as perceptual indications to guide the aggregation of global and unbiased information during hypergraph messaging. Using HGFormer as visual backbone, we develop an effective and unitive representation, achieving distinct and detailed scene depictions. Empirical experiments show that the proposed HGFormer achieves competitive performance compared to the recent SoTA counterparts on various visual benchmarks. Extensive ablation and visualization studies provide comprehensive explanations of our ideas and contributions.
Authors: Jiayi Gao, Zijin Yin, Changcheng Hua, Yuxin Peng, Kongming Liang, Zhanyu Ma, Jun Guo, Yang Liu
Abstract: The development of Text-to-Video (T2V) generation has made motion transfer possible, enabling the control of video motion based on existing footage. However, current methods have two limitations: 1) struggle to handle multi-subjects videos, failing to transfer specific subject motion; 2) struggle to preserve the diversity and accuracy of motion as transferring to subjects with varying shapes. To overcome these, we introduce \textbf{ConMo}, a zero-shot framework that disentangle and recompose the motions of subjects and camera movements. ConMo isolates individual subject and background motion cues from complex trajectories in source videos using only subject masks, and reassembles them for target video generation. This approach enables more accurate motion control across diverse subjects and improves performance in multi-subject scenarios. Additionally, we propose soft guidance in the recomposition stage which controls the retention of original motion to adjust shape constraints, aiding subject shape adaptation and semantic transformation. Unlike previous methods, ConMo unlocks a wide range of applications, including subject size and position editing, subject removal, semantic modifications, and camera motion simulation. Extensive experiments demonstrate that ConMo significantly outperforms state-of-the-art methods in motion fidelity and semantic consistency. The code is available at https://github.com/Andyplus1/ConMo.
Authors: Changshuo Wang, Shuting He, Xiang Fang, Meiqing Wu, Siew-Kei Lam, Prayag Tiwari
Abstract: Few-shot point cloud semantic segmentation aims to accurately segment "unseen" new categories in point cloud scenes using limited labeled data. However, pretraining-based methods not only introduce excessive time overhead but also overlook the local structure representation among irregular point clouds. To address these issues, we propose a pretraining-free local structure fitting network for few-shot point cloud semantic segmentation, named TaylorSeg. Specifically, inspired by Taylor series, we treat the local structure representation of irregular point clouds as a polynomial fitting problem and propose a novel local structure fitting convolution, called TaylorConv. This convolution learns the low-order basic information and high-order refined information of point clouds from explicit encoding of local geometric structures. Then, using TaylorConv as the basic component, we construct two variants of TaylorSeg: a non-parametric TaylorSeg-NN and a parametric TaylorSeg-PN. The former can achieve performance comparable to existing parametric models without pretraining. For the latter, we equip it with an Adaptive Push-Pull (APP) module to mitigate the feature distribution differences between the query set and the support set. Extensive experiments validate the effectiveness of the proposed method. Notably, under the 2-way 1-shot setting, TaylorSeg-PN achieves improvements of +2.28% and +4.37% mIoU on the S3DIS and ScanNet datasets respectively, compared to the previous state-of-the-art methods. Our code is available at https://github.com/changshuowang/TaylorSeg.
Authors: Ruixiao Zhang, Runwei Guan, Xiangyu Chen, Adam Prugel-Bennett, Xiaohao Cai
Abstract: 3D object detection aims to predict object centers, dimensions, and rotations from LiDAR point clouds. Despite its simplicity, LiDAR captures only the near side of objects, making center-based detectors prone to poor localization accuracy in cross-domain tasks with varying point distributions. Meanwhile, existing evaluation metrics designed for single-domain assessment also suffer from overfitting due to dataset-specific size variations. A key question arises: Do we really need models to maintain excellent performance in the entire 3D bounding boxes after being applied across domains? Actually, one of our main focuses is on preventing collisions between vehicles and other obstacles, especially in cross-domain scenarios where correctly predicting the sizes is much more difficult. To address these issues, we rethink cross-domain 3D object detection from a practical perspective. We propose two new metrics that evaluate a model's ability to detect objects' closer-surfaces to the LiDAR sensor. Additionally, we introduce EdgeHead, a refinement head that guides models to focus more on learnable closer surfaces, significantly improving cross-domain performance under both our new and traditional BEV/3D metrics. Furthermore, we argue that predicting the nearest corner rather than the object center enhances robustness. We propose a novel 3D object detector, coined as CornerPoint3D, which is built upon CenterPoint and uses heatmaps to supervise the learning and detection of the nearest corner of each object. Our proposed methods realize a balanced trade-off between the detection quality of entire bounding boxes and the locating accuracy of closer surfaces to the LiDAR sensor, outperforming the traditional center-based detector CenterPoint in multiple cross-domain tasks and providing a more practically reasonable and robust cross-domain 3D object detection solution.
Authors: H{\aa}kon N{\ae}ss Sandum (Faculty of Environmental Sciences and Natural Resource Management, Norwegian University of Life Sciences, NMBU, {\AA}s, Norway), Hans Ole {\O}rka (Faculty of Environmental Sciences and Natural Resource Management, Norwegian University of Life Sciences, NMBU, {\AA}s, Norway), Oliver Tomic (Faculty of Science and Technology, Norwegian University of Life Sciences, NMBU, {\AA}s, Norway), Erik N{\ae}sset (Faculty of Environmental Sciences and Natural Resource Management, Norwegian University of Life Sciences, NMBU, {\AA}s, Norway), Terje Gobakken (Faculty of Environmental Sciences and Natural Resource Management, Norwegian University of Life Sciences, NMBU, {\AA}s, Norway)
Abstract: Forest stands are the fundamental units in forest management inventories, silviculture, and financial analysis within operational forestry. Over the past two decades, a common method for mapping stand borders has involved delineation through manual interpretation of stereographic aerial images. This is a time-consuming and subjective process, limiting operational efficiency and introducing inconsistencies. Substantial effort has been devoted to automating the process, using various algorithms together with aerial images and canopy height models constructed from airborne laser scanning (ALS) data, but manual interpretation remains the preferred method. Deep learning (DL) methods have demonstrated great potential in computer vision, yet their application to forest stand delineation remains unexplored in published research. This study presents a novel approach, framing stand delineation as a multiclass segmentation problem and applying a U-Net based DL framework. The model was trained and evaluated using multispectral images, ALS data, and an existing stand map created by an expert interpreter. Performance was assessed on independent data using overall accuracy, a standard metric for classification tasks that measures the proportions of correctly classified pixels. The model achieved an overall accuracy of 0.73. These results demonstrate strong potential for DL in automated stand delineation. However, a few key challenges were noted, especially for complex forest environments.
Authors: Bizhu Wu, Jinheng Xie, Keming Shen, Zhe Kong, Jianfeng Ren, Ruibin Bai, Rong Qu, Linlin Shen
Abstract: Recent motion-aware large language models have demonstrated promising potential in unifying motion comprehension and generation. However, existing approaches primarily focus on coarse-grained motion-text modeling, where text describes the overall semantics of an entire motion sequence in just a few words. This limits their ability to handle fine-grained motion-relevant tasks, such as understanding and controlling the movements of specific body parts. To overcome this limitation, we pioneer MG-MotionLLM, a unified motion-language model for multi-granular motion comprehension and generation. We further introduce a comprehensive multi-granularity training scheme by incorporating a set of novel auxiliary tasks, such as localizing temporal boundaries of motion segments via detailed text as well as motion detailed captioning, to facilitate mutual reinforcement for motion-text modeling across various levels of granularity. Extensive experiments show that our MG-MotionLLM achieves superior performance on classical text-to-motion and motion-to-text tasks, and exhibits potential in novel fine-grained motion comprehension and editing tasks. Project page: CVI-SZU/MG-MotionLLM
Authors: Kyungmin Choi, JaKeoung Koo, Stephen McLaughlin, Abderrahim Halimi
Abstract: Single-photon Lidar imaging offers a significant advantage in 3D imaging due to its high resolution and long-range capabilities, however it is challenging to apply in noisy environments with multiple targets per pixel. To tackle these challenges, several methods have been proposed. Statistical methods demonstrate interpretability on the inferred parameters, but they are often limited in their ability to handle complex scenes. Deep learning-based methods have shown superior performance in terms of accuracy and robustness, but they lack interpretability or they are limited to a single-peak per pixel. In this paper, we propose a deep unrolling algorithm for dual-peak single-photon Lidar imaging. We introduce a hierarchical Bayesian model for multiple targets and propose a neural network that unrolls the underlying statistical method. To support multiple targets, we adopt a dual depth maps representation and exploit geometric deep learning to extract features from the point cloud. The proposed method takes advantages of statistical methods and learning-based methods in terms of accuracy and quantifying uncertainty. The experimental results on synthetic and real data demonstrate the competitive performance when compared to existing methods, while also providing uncertainty information.
Authors: Faisal Mohammad, Duksan Ryu
Abstract: Semiconductor wafer defect classification is critical for ensuring high precision and yield in manufacturing. Traditional CNN-based models often struggle with class imbalances and recognition of the multiple overlapping defect types in wafer maps. To address these challenges, we propose ViT-Tiny, a lightweight Vision Transformer (ViT) framework optimized for wafer defect classification. Trained on the WM-38k dataset. ViT-Tiny outperforms its ViT-Base counterpart and state-of-the-art (SOTA) models, such as MSF-Trans and CNN-based architectures. Through extensive ablation studies, we determine that a patch size of 16 provides optimal performance. ViT-Tiny achieves an F1-score of 98.4%, surpassing MSF-Trans by 2.94% in four-defect classification, improving recall by 2.86% in two-defect classification, and increasing precision by 3.13% in three-defect classification. Additionally, it demonstrates enhanced robustness under limited labeled data conditions, making it a computationally efficient and reliable solution for real-world semiconductor defect detection.
Authors: Jiuniu Wang, Wenjia Xu, Qingzhong Wang, Antoni B. Chan
Abstract: Recent advances in image captioning have focused on enhancing accuracy by substantially increasing the dataset and model size. While conventional captioning models exhibit high performance on established metrics such as BLEU, CIDEr, and SPICE, the capability of captions to distinguish the target image from other similar images is under-explored. To generate distinctive captions, a few pioneers employed contrastive learning or re-weighted the ground-truth captions. However, these approaches often overlook the relationships among objects in a similar image group (e.g., items or properties within the same album or fine-grained events). In this paper, we introduce a novel approach to enhance the distinctiveness of image captions, namely Group-based Differential Distinctive Captioning Method, which visually compares each image with other images in one similar group and highlights the uniqueness of each image. In particular, we introduce a Group-based Differential Memory Attention (GDMA) module, designed to identify and emphasize object features in an image that are uniquely distinguishable within its image group, i.e., those exhibiting low similarity with objects in other images. This mechanism ensures that such unique object features are prioritized during caption generation for the image, thereby enhancing the distinctiveness of the resulting captions. To further refine this process, we select distinctive words from the ground-truth captions to guide both the language decoder and the GDMA module. Additionally, we propose a new evaluation metric, the Distinctive Word Rate (DisWordRate), to quantitatively assess caption distinctiveness. Quantitative results indicate that the proposed method significantly improves the distinctiveness of several baseline models, and achieves state-of-the-art performance on distinctiveness while not excessively sacrificing accuracy...
Authors: Zhuguanyu Wu, Jiayi Zhang, Jiaxin Chen, Jinyang Guo, Di Huang, Yunhong Wang
Abstract: Vision Transformers (ViTs) have become one of the most commonly used backbones for vision tasks. Despite their remarkable performance, they often suffer significant accuracy drops when quantized for practical deployment, particularly by post-training quantization (PTQ) under ultra-low bits. Recently, reconstruction-based PTQ methods have shown promising performance in quantizing Convolutional Neural Networks (CNNs). However, they fail when applied to ViTs, primarily due to the inaccurate estimation of output importance and the substantial accuracy degradation in quantizing post-GELU activations. To address these issues, we propose \textbf{APHQ-ViT}, a novel PTQ approach based on importance estimation with Average Perturbation Hessian (APH). Specifically, we first thoroughly analyze the current approximation approaches with Hessian loss, and propose an improved average perturbation Hessian loss. To deal with the quantization of the post-GELU activations, we design an MLP Reconstruction (MR) method by replacing the GELU function in MLP with ReLU and reconstructing it by the APH loss on a small unlabeled calibration set. Extensive experiments demonstrate that APHQ-ViT using linear quantizers outperforms existing PTQ methods by substantial margins in 3-bit and 4-bit across different vision tasks. The source code is available at https://github.com/GoatWu/APHQ-ViT.
Authors: Emad Bahrami, Olga Zatsarynna, Gianpiero Francesca, Juergen Gall
Abstract: While there has been substantial progress in temporal action segmentation, the challenge to generalize to unseen views remains unaddressed. Hence, we define a protocol for unseen view action segmentation where camera views for evaluating the model are unavailable during training. This includes changing from top-frontal views to a side view or even more challenging from exocentric to egocentric views. Furthermore, we present an approach for temporal action segmentation that tackles this challenge. Our approach leverages a shared representation at both the sequence and segment levels to reduce the impact of view differences during training. We achieve this by introducing a sequence loss and an action loss, which together facilitate consistent video and action representations across different views. The evaluation on the Assembly101, IkeaASM, and EgoExoLearn datasets demonstrate significant improvements, with a 12.8% increase in F1@50 for unseen exocentric views and a substantial 54% improvement for unseen egocentric views.
Authors: Nedko Savov, Naser Kazemi, Mohammad Mahdi, Danda Pani Paudel, Xi Wang, Luc Van Gool
Abstract: Modern world models require costly and time-consuming collection of large video datasets with action demonstrations by people or by environment-specific agents. To simplify training, we focus on using many virtual environments for inexpensive, automatically collected interaction data. Genie, a recent multi-environment world model, demonstrates simulation abilities of many environments with shared behavior. Unfortunately, training their model requires expensive demonstrations. Therefore, we propose a training framework merely using a random agent in virtual environments. While the model trained in this manner exhibits good controls, it is limited by the random exploration possibilities. To address this limitation, we propose AutoExplore Agent - an exploration agent that entirely relies on the uncertainty of the world model, delivering diverse data from which it can learn the best. Our agent is fully independent of environment-specific rewards and thus adapts easily to new environments. With this approach, the pretrained multi-environment model can quickly adapt to new environments achieving video fidelity and controllability improvement. In order to obtain automatically large-scale interaction datasets for pretraining, we group environments with similar behavior and controls. To this end, we annotate the behavior and controls of 974 virtual environments - a dataset that we name RetroAct. For building our model, we first create an open implementation of Genie - GenieRedux and apply enhancements and adaptations in our version GenieRedux-G. Our code and data are available at https://github.com/insait-institute/GenieRedux.
Authors: Yash Kulthe, Andrew Gilbert, John Collomosse
Abstract: We present MultiNeRF, a 3D watermarking method that embeds multiple uniquely keyed watermarks within images rendered by a single Neural Radiance Field (NeRF) model, whilst maintaining high visual quality. Our approach extends the TensoRF NeRF model by incorporating a dedicated watermark grid alongside the existing geometry and appearance grids. This extension ensures higher watermark capacity without entangling watermark signals with scene content. We propose a FiLM-based conditional modulation mechanism that dynamically activates watermarks based on input identifiers, allowing multiple independent watermarks to be embedded and extracted without requiring model retraining. MultiNeRF is validated on the NeRF-Synthetic and LLFF datasets, with statistically significant improvements in robust capacity without compromising rendering quality. By generalizing single-watermark NeRF methods into a flexible multi-watermarking framework, MultiNeRF provides a scalable solution for 3D content. attribution.
Authors: Christian Alexander Holz, Christian Bader, Markus Enzweiler, Matthias Dr\"uppel
Abstract: This paper presents novel Machine Learning (ML) methodologies for Multi-Object Tracking (MOT), specifically designed to meet the increasing complexity and precision demands of Advanced Driver Assistance Systems (ADAS). We introduce three Neural Network (NN) models that address key challenges in MOT: (i) the Single-Prediction Network (SPENT) for trajectory prediction, (ii) the Single-Association Network (SANT) for mapping individual Sensor Object (SO) to existing tracks, and (iii) the Multi-Association Network (MANTa) for associating multiple SOs to multiple tracks. These models are seamlessly integrated into a traditional Kalman Filter (KF) framework, maintaining the system's modularity by replacing relevant components without disrupting the overall architecture. Importantly, all three networks are designed to be run in a realtime, embedded environment. Each network contains less than 50k trainable parameters. Our evaluation, conducted on the public KITTI tracking dataset, demonstrates significant improvements in tracking performance. SPENT reduces the Root Mean Square Error (RMSE) by 50% compared to a standard KF, while SANT and MANTa achieve up to 95% accuracy in sensor object-to-track assignments. These results underscore the effectiveness of incorporating task-specific NNs into traditional tracking systems, boosting performance and robustness while preserving modularity, maintainability, and interpretability.
Authors: Fatemeh Behrad, Tinne Tuytelaars, Johan Wagemans
Abstract: The capacity of Vision transformers (ViTs) to handle variable-sized inputs is often constrained by computational complexity and batch processing limitations. Consequently, ViTs are typically trained on small, fixed-size images obtained through downscaling or cropping. While reducing computational burden, these methods result in significant information loss, negatively affecting tasks like image aesthetic assessment. We introduce Charm, a novel tokenization approach that preserves Composition, High-resolution, Aspect Ratio, and Multi-scale information simultaneously. Charm prioritizes high-resolution details in specific regions while downscaling others, enabling shorter fixed-size input sequences for ViTs while incorporating essential information. Charm is designed to be compatible with pre-trained ViTs and their learned positional embeddings. By providing multiscale input and introducing variety to input tokens, Charm improves ViT performance and generalizability for image aesthetic assessment. We avoid cropping or changing the aspect ratio to further preserve information. Extensive experiments demonstrate significant performance improvements on various image aesthetic and quality assessment datasets (up to 8.1 %) using a lightweight ViT backbone. Code and pre-trained models are available at https://github.com/FBehrad/Charm.
Authors: Yunhao Lv, Lingyu Chen, Jian Wang, Yangxi Li, Fang Chen
Abstract: In recent years, deep learning methods such as convolutional neural network (CNN) and transformers have made significant progress in CT multi-organ segmentation. However, CT multi-organ segmentation methods based on masked image modeling (MIM) are very limited. There are already methods using MAE for CT multi-organ segmentation task, we believe that the existing methods do not identify the most difficult areas to reconstruct. To this end, we propose a MIM self-training framework with hard patches mining masked autoencoders for CT multi-organ segmentation tasks (selfMedHPM). The method performs ViT self-pretraining on the training set of the target data and introduces an auxiliary loss predictor, which first predicts the patch loss and determines the location of the next mask. SelfMedHPM implementation is better than various competitive methods in abdominal CT multi-organ segmentation and body CT multi-organ segmentation. We have validated the performance of our method on the Multi Atlas Labeling Beyond The Cranial Vault (BTCV) dataset for abdomen mult-organ segmentation and the SinoMed Whole Body (SMWB) dataset for body multi-organ segmentation tasks.
Authors: Mykola Lavreniuk, Nataliia Kussul, Andrii Shelestov, Bohdan Yailymov, Yevhenii Salii, Volodymyr Kuzin, Zoltan Szantoi
Abstract: The accurate delineation of agricultural field boundaries from satellite imagery is vital for land management and crop monitoring. However, current methods face challenges due to limited dataset sizes, resolution discrepancies, and diverse environmental conditions. We address this by reformulating the task as instance segmentation and introducing the Field Boundary Instance Segmentation - 22M dataset (FBIS-22M), a large-scale, multi-resolution dataset comprising 672,909 high-resolution satellite image patches (ranging from 0.25 m to 10 m) and 22,926,427 instance masks of individual fields, significantly narrowing the gap between agricultural datasets and those in other computer vision domains. We further propose Delineate Anything, an instance segmentation model trained on our new FBIS-22M dataset. Our proposed model sets a new state-of-the-art, achieving a substantial improvement of 88.5% in mAP@0.5 and 103% in mAP@0.5:0.95 over existing methods, while also demonstrating significantly faster inference and strong zero-shot generalization across diverse image resolutions and unseen geographic regions. Code, pre-trained models, and the FBIS-22M dataset are available at https://lavreniuk.github.io/Delineate-Anything.
Authors: Konrad Gadzicki, Kerstin Schill, Christoph Zetzsche
Abstract: This paper presents the Sensorimotor Transformer (SMT), a vision model inspired by human saccadic eye movements that prioritize high-saliency regions in visual input to enhance computational efficiency and reduce memory consumption. Unlike traditional models that process all image patches uniformly, SMT identifies and selects the most salient patches based on intrinsic two-dimensional (i2D) features, such as corners and occlusions, which are known to convey high-information content and align with human fixation patterns. The SMT architecture uses this biological principle to leverage vision transformers to process only the most informative patches, allowing for a substantial reduction in memory usage that scales with the sequence length of selected patches. This approach aligns with visual neuroscience findings, suggesting that the human visual system optimizes information gathering through selective, spatially dynamic focus. Experimental evaluations on Imagenet-1k demonstrate that SMT achieves competitive top-1 accuracy while significantly reducing memory consumption and computational complexity, particularly when a limited number of patches is used. This work introduces a saccade-like selection mechanism into transformer-based vision models, offering an efficient alternative for image analysis and providing new insights into biologically motivated architectures for resource-constrained applications.
Authors: Fa-Ting Hong, Zunnan Xu, Zixiang Zhou, Jun Zhou, Xiu Li, Qin Lin, Qinglin Lu, Dan Xu
Abstract: Talking head synthesis is vital for virtual avatars and human-computer interaction. However, most existing methods are typically limited to accepting control from a single primary modality, restricting their practical utility. To this end, we introduce \textbf{ACTalker}, an end-to-end video diffusion framework that supports both multi-signals control and single-signal control for talking head video generation. For multiple control, we design a parallel mamba structure with multiple branches, each utilizing a separate driving signal to control specific facial regions. A gate mechanism is applied across all branches, providing flexible control over video generation. To ensure natural coordination of the controlled video both temporally and spatially, we employ the mamba structure, which enables driving signals to manipulate feature tokens across both dimensions in each branch. Additionally, we introduce a mask-drop strategy that allows each driving signal to independently control its corresponding facial region within the mamba structure, preventing control conflicts. Experimental results demonstrate that our method produces natural-looking facial videos driven by diverse signals and that the mamba layer seamlessly integrates multiple driving modalities without conflict.
Authors: Bo-Kai Ruan, Hong-Han Shuai
Abstract: Existing makeup techniques often require designing multiple models to handle different inputs and align features across domains for different makeup tasks, e.g., beauty filter, makeup transfer, and makeup removal, leading to increased complexity. Another limitation is the absence of text-guided makeup try-on, which is more user-friendly without needing reference images. In this study, we make the first attempt to use a single model for various makeup tasks. Specifically, we formulate different makeup tasks as cross-domain translations and leverage a cross-domain diffusion model to accomplish all tasks. Unlike existing methods that rely on separate encoder-decoder configurations or cycle-based mechanisms, we propose using different domain embeddings to facilitate domain control. This allows for seamless domain switching by merely changing embeddings with a single model, thereby reducing the reliance on additional modules for different tasks. Moreover, to support precise text-to-makeup applications, we introduce the MT-Text dataset by extending the MT dataset with textual annotations, advancing the practicality of makeup technologies.
Authors: Hesong Li, Ziqi Wu, Ruiwen Shao, Tao Zhang, Ying Fu
Abstract: Scanning Transmission Electron Microscopy (STEM) enables the observation of atomic arrangements at sub-angstrom resolution, allowing for atomically resolved analysis of the physical and chemical properties of materials. However, due to the effects of noise, electron beam damage, sample thickness, etc, obtaining satisfactory atomic-level images is often challenging. Enhancing STEM images can reveal clearer structural details of materials. Nonetheless, existing STEM image enhancement methods usually overlook unique features in the frequency domain, and existing datasets lack realism and generality. To resolve these issues, in this paper, we develop noise calibration, data synthesis, and enhancement methods for STEM images. We first present a STEM noise calibration method, which is used to synthesize more realistic STEM images. The parameters of background noise, scan noise, and pointwise noise are obtained by statistical analysis and fitting of real STEM images containing atoms. Then we use these parameters to develop a more general dataset that considers both regular and random atomic arrangements and includes both HAADF and BF mode images. Finally, we design a spatial-frequency interactive network for STEM image enhancement, which can explore the information in the frequency domain formed by the periodicity of atomic arrangement. Experimental results show that our data is closer to real STEM images and achieves better enhancement performances together with our network. Code will be available at https://github.com/HeasonLee/SFIN}{https://github.com/HeasonLee/SFIN.
URLs: https://github.com/HeasonLee/SFIN, https://github.com/HeasonLee/SFIN.
Authors: Andrei Dumitriu, Florin Tatui, Florin Miron, Radu Tudor Ionescu, Radu Timofte
Abstract: Rip currents are the leading cause of fatal accidents and injuries on many beaches worldwide, emphasizing the importance of automatically detecting these hazardous surface water currents. In this paper, we address a novel task: rip current instance segmentation. We introduce a comprehensive dataset containing $2,466$ images with newly created polygonal annotations for instance segmentation, used for training and validation. Additionally, we present a novel dataset comprising $17$ drone videos (comprising about $24K$ frames) captured at $30 FPS$, annotated with both polygons for instance segmentation and bounding boxes for object detection, employed for testing purposes. We train various versions of YOLOv8 for instance segmentation on static images and assess their performance on the test dataset (videos). The best results were achieved by the YOLOv8-nano model (runnable on a portable device), with an mAP50 of $88.94%$ on the validation dataset and $81.21%$ macro average on the test dataset. The results provide a baseline for future research in rip current segmentation. Our work contributes to the existing literature by introducing a detailed, annotated dataset, and training a deep learning model for instance segmentation of rip currents. The code, training details and the annotated dataset are made publicly available at https://github.com/Irikos/rip_currents.
Authors: Yongqi Zhai, Luyang Tang, Wei Jiang, Jiayu Yang, Ronggang Wang
Abstract: Recently, learned video compression (LVC) has shown superior performance under low-delay configuration. However, the performance of learned bi-directional video compression (LBVC) still lags behind traditional bi-directional coding. The performance gap mainly arises from inaccurate long-term motion estimation and prediction of distant frames, especially in large motion scenes. To solve these two critical problems, this paper proposes a novel LBVC framework, namely L-LBVC. Firstly, we propose an adaptive motion estimation module that can handle both short-term and long-term motions. Specifically, we directly estimate the optical flows for adjacent frames and non-adjacent frames with small motions. For non-adjacent frames with large motions, we recursively accumulate local flows between adjacent frames to estimate long-term flows. Secondly, we propose an adaptive motion prediction module that can largely reduce the bit cost for motion coding. To improve the accuracy of long-term motion prediction, we adaptively downsample reference frames during testing to match the motion ranges observed during training. Experiments show that our L-LBVC significantly outperforms previous state-of-the-art LVC methods and even surpasses VVC (VTM) on some test datasets under random access configuration.
Authors: Abdul Rehman, Talha Meraj, Aiman Mahmood Minhas, Ayisha Imran, Mohsen Ali, Waqas Sultani, Mubarak Shah
Abstract: Leukemia is 10th most frequently diagnosed cancer and one of the leading causes of cancer related deaths worldwide. Realistic analysis of Leukemia requires White Blook Cells (WBC) localization, classification, and morphological assessment. Despite deep learning advances in medical imaging, leukemia analysis lacks a large, diverse multi-task dataset, while existing small datasets lack domain diversity, limiting real world applicability. To overcome dataset challenges, we present a large scale WBC dataset named Large Leukemia Dataset (LLD) and novel methods for detecting WBC with their attributes. Our contribution here is threefold. First, we present a large-scale Leukemia dataset collected through Peripheral Blood Films (PBF) from several patients, through multiple microscopes, multi cameras, and multi magnification. To enhance diagnosis explainability and medical expert acceptance, each leukemia cell is annotated at 100x with 7 morphological attributes, ranging from Cell Size to Nuclear Shape. Secondly, we propose a multi task model that not only detects WBCs but also predicts their attributes, providing an interpretable and clinically meaningful solution. Third, we propose a method for WBC detection with attribute analysis using sparse annotations. This approach reduces the annotation burden on hematologists, requiring them to mark only a small area within the field of view. Our method enables the model to leverage the entire field of view rather than just the annotated regions, enhancing learning efficiency and diagnostic accuracy. From diagnosis explainability to overcoming domain shift challenges, presented datasets could be used for many challenging aspects of microscopic image analysis. The datasets, code, and demo are available at: https://im.itu.edu.pk/sparse-leukemiaattri/
Authors: Jiwoo Chung, Sangeek Hyun, Hyunjun Kim, Eunseo Koh, MinKyu Lee, Jae-Pil Heo
Abstract: Recent advances in text-to-image generative models have enabled numerous practical applications, including subject-driven generation, which fine-tunes pretrained models to capture subject semantics from only a few examples. While diffusion-based models produce high-quality images, their extensive denoising steps result in significant computational overhead, limiting real-world applicability. Visual autoregressive~(VAR) models, which predict next-scale tokens rather than spatially adjacent ones, offer significantly faster inference suitable for practical deployment. In this paper, we propose the first VAR-based approach for subject-driven generation. However, na\"{\i}ve fine-tuning VAR leads to computational overhead, language drift, and reduced diversity. To address these challenges, we introduce selective layer tuning to reduce complexity and prior distillation to mitigate language drift. Additionally, we found that the early stages have a greater influence on the generation of subject than the latter stages, which merely synthesize local details. Based on this finding, we propose scale-wise weighted tuning, which prioritizes coarser resolutions for promoting the model to focus on the subject-relevant information instead of local details. Extensive experiments validate that our method significantly outperforms diffusion-based baselines across various metrics and demonstrates its practical usage.
Authors: Lihua Liu, Jiehong Lin, Zhenxin Liu, Kui Jia
Abstract: Novel object pose estimation from RGB images presents a significant challenge for zero-shot generalization, as it involves estimating the relative 6D transformation between an RGB observation and a CAD model of an object that was not seen during training. In this paper, we introduce PicoPose, a novel framework designed to tackle this task using a three-stage pixel-to-pixel correspondence learning process. Firstly, PicoPose matches features from the RGB observation with those from rendered object templates, identifying the best-matched template and establishing coarse correspondences. Secondly, PicoPose smooths the correspondences by globally regressing a 2D affine transformation, including in-plane rotation, scale, and 2D translation, from the coarse correspondence map. Thirdly, PicoPose applies the affine transformation to the feature map of the best-matched template and learns correspondence offsets within local regions to achieve fine-grained correspondences. By progressively refining the correspondences, PicoPose significantly improves the accuracy of object poses computed via PnP/RANSAC. PicoPose achieves state-of-the-art performance on the seven core datasets of the BOP benchmark, demonstrating exceptional generalization to novel objects represented by CAD models or object reference images. Code and models are available at https://github.com/foollh/PicoPose.
Authors: Xingguang Zhang, Nicholas Chimitt, Xijun Wang, Yu Yuan, Stanley H. Chan
Abstract: Atmospheric turbulence is a major source of image degradation in long-range imaging systems. Although numerous deep learning-based turbulence mitigation (TM) methods have been proposed, many are slow, memory-hungry, and do not generalize well. In the spatial domain, methods based on convolutional operators have a limited receptive field, so they cannot handle a large spatial dependency required by turbulence. In the temporal domain, methods relying on self-attention can, in theory, leverage the lucky effects of turbulence, but their quadratic complexity makes it difficult to scale to many frames. Traditional recurrent aggregation methods face parallelization challenges. In this paper, we present a new TM method based on two concepts: (1) A turbulence mitigation network based on the Selective State Space Model (MambaTM). MambaTM provides a global receptive field in each layer across spatial and temporal dimensions while maintaining linear computational complexity. (2) Learned Latent Phase Distortion (LPD). LPD guides the state space model. Unlike classical Zernike-based representations of phase distortion, the new LPD map uniquely captures the actual effects of turbulence, significantly improving the model's capability to estimate degradation by reducing the ill-posedness. Our proposed method exceeds current state-of-the-art networks on various synthetic and real-world TM benchmarks with significantly faster inference speed. The code is available at http://github.com/xg416/MambaTM.
Authors: Hui Zhang, Qinglin Zhao, Mengchu Zhou, Li Feng
Abstract: Transformer-based architectures have revolutionized the landscape of deep learning. In computer vision domain, Vision Transformer demonstrates remarkable performance on par with or even surpassing that of convolutional neural networks. However, the quadratic computational complexity of its self-attention mechanism poses challenges for classical computing, making model training with high-dimensional input data, e.g., images, particularly expensive. To address such limitations, we propose a Hybrid Quantum Vision Transformer (HQViT), that leverages the principles of quantum computing to accelerate model training while enhancing model performance. HQViT introduces whole-image processing with amplitude encoding to better preserve global image information without additional positional encoding. By leveraging quantum computation on the most critical steps and selectively handling other components in a classical way, we lower the cost of quantum resources for HQViT. The qubit requirement is minimized to $O(log_2N)$ and the number of parameterized quantum gates is only $O(log_2d)$, making it well-suited for Noisy Intermediate-Scale Quantum devices. By offloading the computationally intensive attention coefficient matrix calculation to the quantum framework, HQViT reduces the classical computational load by $O(T^2d)$. Extensive experiments across various computer vision datasets demonstrate that HQViT outperforms existing models, achieving a maximum improvement of up to $10.9\%$ (on the MNIST 10-classification task) over the state of the art. This work highlights the great potential to combine quantum and classical computing to cope with complex image classification tasks.
Authors: Ahmet Burak Yildirim, Mustafa Utku Aydogdu, Duygu Ceylan, Aysegul Dundar
Abstract: We introduce MD-ProjTex, a method for fast and consistent text-guided texture generation for 3D shapes using pretrained text-to-image diffusion models. At the core of our approach is a multi-view consistency mechanism in UV space, which ensures coherent textures across different viewpoints. Specifically, MD-ProjTex fuses noise predictions from multiple views at each diffusion step and jointly updates the per-view denoising directions to maintain 3D consistency. In contrast to existing state-of-the-art methods that rely on optimization or sequential view synthesis, MD-ProjTex is computationally more efficient and achieves better quantitative and qualitative results.
Authors: Benjy Friedmann, Michael Werman
Abstract: Point cloud processing poses two fundamental challenges: establishing consistent point ordering and effectively learning fine-grained geometric features. Current architectures rely on complex operations that limit expressivity while struggling to capture detailed surface geometry. We present CanonNet, a lightweight neural network composed of two complementary components: (1) a preprocessing pipeline that creates a canonical point ordering and orientation, and (2) a geometric learning framework where networks learn from synthetic surfaces with precise curvature values. This modular approach eliminates the need for complex transformation-invariant architectures while effectively capturing local geometric properties. Our experiments demonstrate state-of-the-art performance in curvature estimation and competitive results in geometric descriptor tasks with significantly fewer parameters (\textbf{100X}) than comparable methods. CanonNet's efficiency makes it particularly suitable for real-world applications where computational resources are limited, demonstrating that mathematical preprocessing can effectively complement neural architectures for point cloud analysis. The code for the project is publicly available \hyperlink{https://benjyfri.github.io/CanonNet/}{https://benjyfri.github.io/CanonNet/}.
URLs: https://benjyfri.github.io/CanonNet/, https://benjyfri.github.io/CanonNet/
Authors: Shengjun Zhang, Jinzhao Li, Xin Fei, Hao Liu, Yueqi Duan
Abstract: In this paper, we propose Scene Splatter, a momentum-based paradigm for video diffusion to generate generic scenes from single image. Existing methods, which employ video generation models to synthesize novel views, suffer from limited video length and scene inconsistency, leading to artifacts and distortions during further reconstruction. To address this issue, we construct noisy samples from original features as momentum to enhance video details and maintain scene consistency. However, for latent features with the perception field that spans both known and unknown regions, such latent-level momentum restricts the generative ability of video diffusion in unknown regions. Therefore, we further introduce the aforementioned consistent video as a pixel-level momentum to a directly generated video without momentum for better recovery of unseen regions. Our cascaded momentum enables video diffusion models to generate both high-fidelity and consistent novel views. We further finetune the global Gaussian representations with enhanced frames and render new frames for momentum update in the next step. In this manner, we can iteratively recover a 3D scene, avoiding the limitation of video length. Extensive experiments demonstrate the generalization capability and superior performance of our method in high-fidelity and consistent scene generation.
Authors: Yoon Gyo Jung, Jaewoo Park, Jaeho Yoon, Kuan-Chuan Peng, Wonchul Kim, Andrew Beng Jin Teoh, Octavia Camps
Abstract: We aim to solve unsupervised anomaly detection in a practical challenging environment where the normal dataset is both contaminated with defective regions and its product class distribution is tailed but unknown. We observe that existing models suffer from tail-versus-noise trade-off where if a model is robust against pixel noise, then its performance deteriorates on tail class samples, and vice versa. To mitigate the issue, we handle the tail class and noise samples independently. To this end, we propose TailSampler, a novel class size predictor that estimates the class cardinality of samples based on a symmetric assumption on the class-wise distribution of embedding similarities. TailSampler can be utilized to sample the tail class samples exclusively, allowing to handle them separately. Based on these facets, we build a memory-based anomaly detection model TailedCore, whose memory both well captures tail class information and is noise-robust. We extensively validate the effectiveness of TailedCore on the unsupervised long-tail noisy anomaly detection setting, and show that TailedCore outperforms the state-of-the-art in most settings.
Authors: Vincent Gbouna Zakka, Luis J. Manso, Zhuangzhuang Dai
Abstract: Human activity recognition is increasingly vital for supporting independent living, particularly for the elderly and those in need of assistance. Domestic service robots with monitoring capabilities can enhance safety and provide essential support. Although image-based methods have advanced considerably in the past decade, their adoption remains limited by concerns over privacy and sensitivity to low-light or dark conditions. As an alternative, millimetre-wave (mmWave) radar can produce point cloud data which is privacy-preserving. However, processing the sparse and noisy point clouds remains a long-standing challenge. While graph-based methods and attention mechanisms show promise, they predominantly rely on "fixed" kernels; kernels that are applied uniformly across all neighbourhoods, highlighting the need for adaptive approaches that can dynamically adjust their kernels to the specific geometry of each local neighbourhood in point cloud data. To overcome this limitation, we introduce an adaptive approach within the graph convolutional framework. Instead of a single shared weight function, our Multi-Head Adaptive Kernel (MAK) module generates multiple dynamic kernels, each capturing different aspects of the local feature space. By progressively refining local features while maintaining global spatial context, our method enables convolution kernels to adapt to varying local features. Experimental results on benchmark datasets confirm the effectiveness of our approach, achieving state-of-the-art performance in human activity recognition. Our source code is made publicly available at: https://github.com/Gbouna/MAK-GCN
Authors: Zhiyuan Yan, Junyan Ye, Weijia Li, Zilong Huang, Shenghai Yuan, Xiangyang He, Kaiqing Lin, Jun He, Conghui He, Li Yuan
Abstract: The recent breakthroughs in OpenAI's GPT4o model have demonstrated surprisingly good capabilities in image generation and editing, resulting in significant excitement in the community. This technical report presents the first-look evaluation benchmark (named GPT-ImgEval), quantitatively and qualitatively diagnosing GPT-4o's performance across three critical dimensions: (1) generation quality, (2) editing proficiency, and (3) world knowledge-informed semantic synthesis. Across all three tasks, GPT-4o demonstrates strong performance, significantly surpassing existing methods in both image generation control and output quality, while also showcasing exceptional knowledge reasoning capabilities. Furthermore, based on the GPT-4o's generated data, we propose a classification-model-based approach to investigate the underlying architecture of GPT-4o, where our empirical results suggest the model consists of an auto-regressive (AR) combined with a diffusion-based head for image decoding, rather than the VAR-like architectures. We also provide a complete speculation on GPT-4o's overall architecture. In addition, we conduct a series of analyses to identify and visualize GPT-4o's specific limitations and the synthetic artifacts commonly observed in its image generation. We also present a comparative study of multi-round image editing between GPT-4o and Gemini 2.0 Flash, and discuss the safety implications of GPT-4o's outputs, particularly their detectability by existing image forensic models. We hope that our work can offer valuable insight and provide a reliable benchmark to guide future research, foster reproducibility, and accelerate innovation in the field of image generation and beyond. The codes and datasets used for evaluating GPT-4o can be found at https://github.com/PicoTrex/GPT-ImgEval.
Authors: Anita Rau, Mark Endo, Josiah Aklilu, Jaewoo Heo, Khaled Saab, Alberto Paderno, Jeffrey Jopling, F. Christopher Holsinger, Serena Yeung-Levy
Abstract: Large Vision-Language Models offer a new paradigm for AI-driven image understanding, enabling models to perform tasks without task-specific training. This flexibility holds particular promise across medicine, where expert-annotated data is scarce. Yet, VLMs' practical utility in intervention-focused domains--especially surgery, where decision-making is subjective and clinical scenarios are variable--remains uncertain. Here, we present a comprehensive analysis of 11 state-of-the-art VLMs across 17 key visual understanding tasks in surgical AI--from anatomy recognition to skill assessment--using 13 datasets spanning laparoscopic, robotic, and open procedures. In our experiments, VLMs demonstrate promising generalizability, at times outperforming supervised models when deployed outside their training setting. In-context learning, incorporating examples during testing, boosted performance up to three-fold, suggesting adaptability as a key strength. Still, tasks requiring spatial or temporal reasoning remained difficult. Beyond surgery, our findings offer insights into VLMs' potential for tackling complex and dynamic scenarios in clinical and broader real-world applications.
Authors: Jay N. Paranjape, Celso de Melo, Vishal M. Patel
Abstract: Thermal imaging is crucial for scene understanding, particularly in low-light and nighttime conditions. However, collecting large thermal datasets is costly and labor-intensive due to the specialized equipment required for infrared image capture. To address this challenge, researchers have explored visible-to-thermal image translation. Most existing methods rely on Generative Adversarial Networks (GANs) or Diffusion Models (DMs), treating the task as a style transfer problem. As a result, these approaches attempt to learn both the modality distribution shift and underlying physical principles from limited training data. In this paper, we propose F-ViTA, a novel approach that leverages the general world knowledge embedded in foundation models to guide the diffusion process for improved translation. Specifically, we condition an InstructPix2Pix Diffusion Model with zero-shot masks and labels from foundation models such as SAM and Grounded DINO. This allows the model to learn meaningful correlations between scene objects and their thermal signatures in infrared imagery. Extensive experiments on five public datasets demonstrate that F-ViTA outperforms state-of-the-art (SOTA) methods. Furthermore, our model generalizes well to out-of-distribution (OOD) scenarios and can generate Long-Wave Infrared (LWIR), Mid-Wave Infrared (MWIR), and Near-Infrared (NIR) translations from the same visible image. Code: https://github.com/JayParanjape/F-ViTA/tree/master.
Authors: Van Nguyen Nguyen, Stephen Tyree, Andrew Guo, Mederic Fourmy, Anas Gouda, Taeyeop Lee, Sungphill Moon, Hyeontae Son, Lukas Ranftl, Jonathan Tremblay, Eric Brachmann, Bertram Drost, Vincent Lepetit, Carsten Rother, Stan Birchfield, Jiri Matas, Yann Labbe, Martin Sundermeyer, Tomas Hodan
Abstract: We present the evaluation methodology, datasets and results of the BOP Challenge 2024, the sixth in a series of public competitions organized to capture the state of the art in 6D object pose estimation and related tasks. In 2024, our goal was to transition BOP from lab-like setups to real-world scenarios. First, we introduced new model-free tasks, where no 3D object models are available and methods need to onboard objects just from provided reference videos. Second, we defined a new, more practical 6D object detection task where identities of objects visible in a test image are not provided as input. Third, we introduced new BOP-H3 datasets recorded with high-resolution sensors and AR/VR headsets, closely resembling real-world scenarios. BOP-H3 include 3D models and onboarding videos to support both model-based and model-free tasks. Participants competed on seven challenge tracks, each defined by a task, object onboarding setup, and dataset group. Notably, the best 2024 method for model-based 6D localization of unseen objects (FreeZeV2.1) achieves 22% higher accuracy on BOP-Classic-Core than the best 2023 method (GenFlow), and is only 4% behind the best 2023 method for seen objects (GPose2023) although being significantly slower (24.9 vs 2.7s per image). A more practical 2024 method for this task is Co-op which takes only 0.8s per image and is 25X faster and 13% more accurate than GenFlow. Methods have a similar ranking on 6D detection as on 6D localization but higher run time. On model-based 2D detection of unseen objects, the best 2024 method (MUSE) achieves 21% relative improvement compared to the best 2023 method (CNOS). However, the 2D detection accuracy for unseen objects is still noticealy (-53%) behind the accuracy for seen objects (GDet2023). The online evaluation system stays open and is available at http://bop.felk.cvut.cz/
URLs: http://bop.felk.cvut.cz/
Authors: Kangle Deng, Hsueh-Ti Derek Liu, Yiheng Zhu, Xiaoxia Sun, Chong Shang, Kiran Bhat, Deva Ramanan, Jun-Yan Zhu, Maneesh Agrawala, Tinghui Zhou
Abstract: Many 3D generative models rely on variational autoencoders (VAEs) to learn compact shape representations. However, existing methods encode all shapes into a fixed-size token, disregarding the inherent variations in scale and complexity across 3D data. This leads to inefficient latent representations that can compromise downstream generation. We address this challenge by introducing Octree-based Adaptive Tokenization, a novel framework that adjusts the dimension of latent representations according to shape complexity. Our approach constructs an adaptive octree structure guided by a quadric-error-based subdivision criterion and allocates a shape latent vector to each octree cell using a query-based transformer. Building upon this tokenization, we develop an octree-based autoregressive generative model that effectively leverages these variable-sized representations in shape generation. Extensive experiments demonstrate that our approach reduces token counts by 50% compared to fixed-size methods while maintaining comparable visual quality. When using a similar token length, our method produces significantly higher-quality shapes. When incorporated with our downstream generative model, our method creates more detailed and diverse 3D content than existing approaches.
Authors: Yuexi Du, Jiazhen Zhang, Nicha C. Dvornek, John A. Onofrey
Abstract: Symmetry, where certain features remain invariant under geometric transformations, can often serve as a powerful prior in designing convolutional neural networks (CNNs). While conventional CNNs inherently support translational equivariance, extending this property to rotation and reflection has proven challenging, often forcing a compromise between equivariance, efficiency, and information loss. In this work, we introduce Gaussian Mixture Ring Convolution (GMR-Conv), an efficient convolution kernel that smooths radial symmetry using a mixture of Gaussian-weighted rings. This design mitigates discretization errors of circular kernels, thereby preserving robust rotation and reflection equivariance without incurring computational overhead. We further optimize both the space and speed efficiency of GMR-Conv via a novel parameterization and computation strategy, allowing larger kernels at an acceptable cost. Extensive experiments on eight classification and one segmentation datasets demonstrate that GMR-Conv not only matches conventional CNNs' performance but can also surpass it in applications with orientation-less data. GMR-Conv is also proven to be more robust and efficient than the state-of-the-art equivariant learning methods. Our work provides inspiring empirical evidence that carefully applied radial symmetry can alleviate the challenges of information loss, marking a promising advance in equivariant network architectures. The code is available at https://github.com/XYPB/GMR-Conv.
Authors: Mateusz Pach, Shyamgopal Karthik, Quentin Bouniot, Serge Belongie, Zeynep Akata
Abstract: Sparse Autoencoders (SAEs) have recently been shown to enhance interpretability and steerability in Large Language Models (LLMs). In this work, we extend the application of SAEs to Vision-Language Models (VLMs), such as CLIP, and introduce a comprehensive framework for evaluating monosemanticity in vision representations. Our experimental results reveal that SAEs trained on VLMs significantly enhance the monosemanticity of individual neurons while also exhibiting hierarchical representations that align well with expert-defined structures (e.g., iNaturalist taxonomy). Most notably, we demonstrate that applying SAEs to intervene on a CLIP vision encoder, directly steer output from multimodal LLMs (e.g., LLaVA) without any modifications to the underlying model. These findings emphasize the practicality and efficacy of SAEs as an unsupervised approach for enhancing both the interpretability and control of VLMs.
Authors: Divya Velayudhan, Abdelfatah Ahmed, Mohamad Alansari, Neha Gour, Abderaouf Behouch, Taimur Hassan, Syed Talal Wasim, Nabil Maalej, Muzammal Naseer, Juergen Gall, Mohammed Bennamoun, Ernesto Damiani, Naoufel Werghi
Abstract: Advancements in Computer-Aided Screening (CAS) systems are essential for improving the detection of security threats in X-ray baggage scans. However, current datasets are limited in representing real-world, sophisticated threats and concealment tactics, and existing approaches are constrained by a closed-set paradigm with predefined labels. To address these challenges, we introduce STCray, the first multimodal X-ray baggage security dataset, comprising 46,642 image-caption paired scans across 21 threat categories, generated using an X-ray scanner for airport security. STCray is meticulously developed with our specialized protocol that ensures domain-aware, coherent captions, that lead to the multi-modal instruction following data in X-ray baggage security. This allows us to train a domain-aware visual AI assistant named STING-BEE that supports a range of vision-language tasks, including scene comprehension, referring threat localization, visual grounding, and visual question answering (VQA), establishing novel baselines for multi-modal learning in X-ray baggage security. Further, STING-BEE shows state-of-the-art generalization in cross-domain settings. Code, data, and models are available at https://divs1159.github.io/STING-BEE/.
Authors: Xiangyu Zhao, Peiyuan Zhang, Kexian Tang, Hao Li, Zicheng Zhang, Guangtao Zhai, Junchi Yan, Hua Yang, Xue Yang, Haodong Duan
Abstract: Large Multi-modality Models (LMMs) have made significant progress in visual understanding and generation, but they still face challenges in General Visual Editing, particularly in following complex instructions, preserving appearance consistency, and supporting flexible input formats. To address this gap, we introduce RISEBench, the first benchmark for evaluating Reasoning-Informed viSual Editing (RISE). RISEBench focuses on four key reasoning types: Temporal, Causal, Spatial, and Logical Reasoning. We curate high-quality test cases for each category and propose an evaluation framework that assesses Instruction Reasoning, Appearance Consistency, and Visual Plausibility with both human judges and an LMM-as-a-judge approach. Our experiments reveal that while GPT-4o-Native significantly outperforms other open-source and proprietary models, even this state-of-the-art system struggles with logical reasoning tasks, highlighting an area that remains underexplored. As an initial effort, RISEBench aims to provide foundational insights into reasoning-aware visual editing and to catalyze future research. Though still in its early stages, we are committed to continuously expanding and refining the benchmark to support more comprehensive, reliable, and scalable evaluations of next-generation multimodal systems. Our code and data will be released at https://github.com/PhoenixZ810/RISEBench.
Authors: Jinqi Luo, Tianjiao Ding, Kwan Ho Ryan Chan, Hancheng Min, Chris Callison-Burch, Ren\'e Vidal
Abstract: Diffusion models are widely used for image editing tasks. Existing editing methods often design a representation manipulation procedure by curating an edit direction in the text embedding or score space. However, such a procedure faces a key challenge: overestimating the edit strength harms visual consistency while underestimating it fails the editing task. Notably, each source image may require a different editing strength, and it is costly to search for an appropriate strength via trial-and-error. To address this challenge, we propose Concept Lancet (CoLan), a zero-shot plug-and-play framework for principled representation manipulation in diffusion-based image editing. At inference time, we decompose the source input in the latent (text embedding or diffusion score) space as a sparse linear combination of the representations of the collected visual concepts. This allows us to accurately estimate the presence of concepts in each image, which informs the edit. Based on the editing task (replace/add/remove), we perform a customized concept transplant process to impose the corresponding editing direction. To sufficiently model the concept space, we curate a conceptual representation dataset, CoLan-150K, which contains diverse descriptions and scenarios of visual terms and phrases for the latent dictionary. Experiments on multiple diffusion-based image editing baselines show that methods equipped with CoLan achieve state-of-the-art performance in editing effectiveness and consistency preservation.
Authors: Ilir Tahiraj, Markus Edinger, Dominik Kulmer, Markus Lienkamp
Abstract: In autonomous systems, sensor calibration is essential for a safe and efficient navigation in dynamic environments. Accurate calibration is a prerequisite for reliable perception and planning tasks such as object detection and obstacle avoidance. Many existing LiDAR calibration methods require overlapping fields of view, while others use external sensing devices or postulate a feature-rich environment. In addition, Sensor-to-Vehicle calibration is not supported by the vast majority of calibration algorithms. In this work, we propose a novel target-based technique for extrinsic Sensor-to-Sensor and Sensor-to-Vehicle calibration of multi-LiDAR systems called CaLiV. This algorithm works for non-overlapping FoVs, as well as arbitrary calibration targets, and does not require any external sensing devices. First, we apply motion to produce FoV overlaps and utilize a simple unscented Kalman filter to obtain vehicle poses. Then, we use the Gaussian mixture model-based registration framework GMMCalib to align the point clouds in a common calibration frame. Finally, we reduce the task of recovering the sensor extrinsics to a minimization problem. We show that both translational and rotational Sensor-to-Sensor errors can be solved accurately by our method. In addition, all Sensor-to-Vehicle rotation angles can also be calibrated with high accuracy. We validate the simulation results in real-world experiments. The code is open source and available on https://github.com/TUMFTM/CaLiV.
Authors: Suman Raj, Bhavani A Madhabhavi, Madhav Kumar, Prabhav Gupta, Yogesh Simmhan
Abstract: Autonomous navigation by drones using onboard sensors, combined with deep learning and computer vision algorithms, is impacting a number of domains. We examine the use of drones to autonomously assist Visually Impaired People (VIPs) in navigating outdoor environments while avoiding obstacles. Here, we present NOVA, a robust calibration technique using depth maps to estimate absolute distances to obstacles in a campus environment. NOVA uses a dynamic-update method that can adapt to adversarial scenarios. We compare NOVA with SOTA depth map approaches, and with geometric and regression-based baseline models, for distance estimation to VIPs and other obstacles in diverse and dynamic conditions. We also provide exhaustive evaluations to validate the robustness and generalizability of our methods. NOVA predicts distances to VIP with an error <30cm and to different obstacles like cars and bicycles with a maximum of 60cm error, which are better than the baselines. NOVA also clearly out-performs SOTA depth map methods, by upto 5.3-14.6x.
Authors: Yi Yao, Miao Fan, Shengtong Xu, Haoyi Xiong, Xiangzeng Liu, Wenbo Hu, Wenbing Huang
Abstract: Lane topology reasoning techniques play a crucial role in high-definition (HD) mapping and autonomous driving applications. While recent years have witnessed significant advances in this field, there has been limited effort to consolidate these works into a comprehensive overview. This survey systematically reviews the evolution and current state of lane topology reasoning methods, categorizing them into three major paradigms: procedural modeling-based methods, aerial imagery-based methods, and onboard sensors-based methods. We analyze the progression from early rule-based approaches to modern learning-based solutions utilizing transformers, graph neural networks (GNNs), and other deep learning architectures. The paper examines standardized evaluation metrics, including road-level measures (APLS and TLTS score), and lane-level metrics (DET and TOP score), along with performance comparisons on benchmark datasets such as OpenLane-V2. We identify key technical challenges, including dataset availability and model efficiency, and outline promising directions for future research. This comprehensive review provides researchers and practitioners with insights into the theoretical frameworks, practical implementations, and emerging trends in lane topology reasoning for HD mapping applications.
Authors: Khizar Anjum, Parul Pandey, Vidyasagar Sadhu, Roberto Tron, Dario Pompili
Abstract: Most applications in autonomous navigation using mounted cameras rely on the construction and processing of geometric 3D point clouds, which is an expensive process. However, there is another simpler way to make a space navigable quickly: to use semantic information (e.g., traffic signs) to guide the agent. However, detecting and acting on semantic information involves Computer Vision~(CV) algorithms such as object detection, which themselves are demanding for agents such as aerial drones with limited onboard resources. To solve this problem, we introduce a novel Markov Decision Process~(MDP) framework to reduce the workload of these CV approaches. We apply our proposed framework to both feature-based and neural-network-based object-detection tasks, using open-loop and closed-loop simulations as well as hardware-in-the-loop emulations. These holistic tests show significant benefits in energy consumption and speed with only a limited loss in accuracy compared to models based on static features and neural networks.
Authors: Zhaoyang Zhang, Yannick Hold-Geoffroy, Milo\v{s} Ha\v{s}an, Chen Ziwen, Fujun Luan, Julie Dorsey, Yiwei Hu
Abstract: Scene-level 3D generation is a challenging research topic, with most existing methods generating only partial scenes and offering limited navigational freedom. We introduce WorldPrompter, a novel generative pipeline for synthesizing traversable 3D scenes from text prompts. We leverage panoramic videos as an intermediate representation to model the 360{\deg} details of a scene. WorldPrompter incorporates a conditional 360{\deg} panoramic video generator, capable of producing a 128-frame video that simulates a person walking through and capturing a virtual environment. The resulting video is then reconstructed as Gaussian splats by a fast feedforward 3D reconstructor, enabling a true walkable experience within the 3D scene. Experiments demonstrate that our panoramic video generation model achieves convincing view consistency across frames, enabling high-quality panoramic Gaussian splat reconstruction and facilitating traversal over an area of the scene. Qualitative and quantitative results also show it outperforms the state-of-the-art 360{\deg} video generators and 3D scene generation models.
Authors: Nick Chodura, Melissa Greeff, Joshua Woods
Abstract: Rooftop 3D reconstruction using UAV-based photogrammetry offers a promising solution for infrastructure assessment, but existing methods often require high percentages of image overlap and extended flight times to ensure model accuracy when using autonomous flight paths. This study systematically evaluates key flight parameters-ground sampling distance (GSD) and image overlap-to optimize the 3D reconstruction of complex rooftop infrastructure. Controlled UAV flights were conducted over a multi-segment rooftop at Queen's University using a DJI Phantom 4 Pro V2, with varied GSD and overlap settings. The collected data were processed using Reality Capture software and evaluated against ground truth models generated from UAV-based LiDAR and terrestrial laser scanning (TLS). Experimental results indicate that a GSD range of 0.75-1.26 cm combined with 85% image overlap achieves a high degree of model accuracy, while minimizing images collected and flight time. These findings provide guidance for planning autonomous UAV flight paths for efficient rooftop assessments.
Authors: Ezzeldin Shereen, Dan Ristea, Burak Hasircioglu, Shae McFadden, Vasilios Mavroudis, Chris Hicks
Abstract: Multimodal retrieval augmented generation (M-RAG) has recently emerged as a method to inhibit hallucinations of large multimodal models (LMMs) through a factual knowledge base (KB). However, M-RAG also introduces new attack vectors for adversaries that aim to disrupt the system by injecting malicious entries into the KB. In this work, we present a poisoning attack against M-RAG targeting visual document retrieval applications, where the KB contains images of document pages. Our objective is to craft a single image that is retrieved for a variety of different user queries, and consistently influences the output produced by the generative model, thus creating a universal denial-of-service (DoS) attack against the M-RAG system. We demonstrate that while our attack is effective against a diverse range of widely-used, state-of-the-art retrievers (embedding models) and generators (LMMs), it can also be ineffective against robust embedding models. Our attack not only highlights the vulnerability of M-RAG pipelines to poisoning attacks, but also sheds light on a fundamental weakness that potentially hinders their performance even in benign settings.
Authors: Jiztom Kavalakkatt Francis, Matthew J Darr
Abstract: The rapid use of artificial intelligence (AI) in processes such as coding, image processing, and data prediction means it is crucial to understand and validate the data we are working with fully. This paper dives into the hurdles of analyzing high-dimensional data, especially when it gets too complex. Traditional methods in data analysis often look at direct connections between input variables, which can miss out on the more complicated relationships within the data. To address these issues, we explore several tested techniques, such as removing specific variables to see their impact and using statistical analysis to find connections between multiple variables. We also consider the role of synthetic data and how information can sometimes be redundant across different sensors. These analyses are typically very computationally demanding and often require much human effort to make sense of the results. A common approach is to treat the entire dataset as one unit and apply advanced models to handle it. However, this can become problematic with larger, noisier datasets and more complex models. So, we suggest methods to identify overall patterns that can help with tasks like classification or regression based on the idea that more straightforward approaches might be more understandable. Our research looks at two datasets: a real-world dataset and a synthetic one. The goal is to create a methodology that highlights key features on a global scale that lead to predictions, making it easier to validate or quantify the data set. By reducing the dimensionality with this method, we can simplify the models used and thus clarify the insights we gain. Furthermore, our method can reveal unexplored relationships between specific inputs and outcomes, providing a way to validate these new connections further.
Authors: Zhen Meng, Kan Chen, Xiangmin Xu, Erwin Jose Lopez Pulgarin, Emma Li, Philip G. Zhao, David Flynn
Abstract: Active 3D scene representation is pivotal in modern robotics applications, including remote inspection, manipulation, and telepresence. Traditional methods primarily optimize geometric fidelity or rendering accuracy, but often overlook operator-specific objectives, such as safety-critical coverage or task-driven viewpoints. This limitation leads to suboptimal viewpoint selection, particularly in constrained environments such as nuclear decommissioning. To bridge this gap, we introduce a novel framework that integrates expert operator preferences into the active 3D scene representation pipeline. Specifically, we employ Reinforcement Learning from Human Feedback (RLHF) to guide robotic path planning, reshaping the reward function based on expert input. To capture operator-specific priorities, we conduct interactive choice experiments that evaluate user preferences in 3D scene representation. We validate our framework using a UR3e robotic arm for reactor tile inspection in a nuclear decommissioning scenario. Compared to baseline methods, our approach enhances scene representation while optimizing trajectory efficiency. The RLHF-based policy consistently outperforms random selection, prioritizing task-critical details. By unifying explicit 3D geometric modeling with implicit human-in-the-loop optimization, this work establishes a foundation for adaptive, safety-critical robotic perception systems, paving the way for enhanced automation in nuclear decommissioning, remote maintenance, and other high-risk environments.
Authors: Lewis Matheson Creed
Abstract: The limited availability of training data for low-resource languages makes applying machine learning techniques challenging. Ancient Egyptian is one such language with few resources. However, innovative applications of data augmentation methods, such as Neural Style Transfer, could overcome these barriers. This paper presents a novel method for generating datasets of ancient Egyptian hieroglyphs by applying NST to a digital typeface. Experimental results found that image classification models trained on NST-generated examples and photographs demonstrate equal performance and transferability to real unseen images of hieroglyphs.
Authors: Samuel Fern\'andez-Mendui\~na, Eduardo Pavez, Antonio Ortega
Abstract: Many images and videos are primarily processed by computer vision algorithms, involving only occasional human inspection. When this content requires compression before processing, e.g., in distributed applications, coding methods must optimize for both visual quality and downstream task performance. We first show that, given the features obtained from the original and the decoded images, an approach to reduce the effect of compression on a task loss is to perform rate-distortion optimization (RDO) using the distance between features as a distortion metric. However, optimizing directly such a rate-distortion trade-off requires an iterative workflow of encoding, decoding, and feature evaluation for each coding parameter, which is computationally impractical. We address this problem by simplifying the RDO formulation to make the distortion term computable using block-based encoders. We first apply Taylor's expansion to the feature extractor, recasting the feature distance as a quadratic metric with the Jacobian matrix of the neural network. Then, we replace the linearized metric with a block-wise approximation, which we call input-dependent squared error (IDSE). To reduce computational complexity, we approximate IDSE using Jacobian sketches. The resulting loss can be evaluated block-wise in the transform domain and combined with the sum of squared errors (SSE) to address both visual quality and computer vision performance. Simulations with AVC across multiple feature extractors and downstream neural networks show up to 10% bit-rate savings for the same computer vision accuracy compared to RDO based on SSE, with no decoder complexity overhead and just a 7% encoder complexity increase.
Authors: Liying Xu, Hongliang He, Wei Han, Hanbin Huang, Siwei Feng, Guohong Fu
Abstract: Nuclear instance segmentation and classification provide critical quantitative foundations for digital pathology diagnosis. With the advent of the foundational Segment Anything Model (SAM), the accuracy and efficiency of nuclear segmentation have improved significantly. However, SAM imposes a strong reliance on precise prompts, and its class-agnostic design renders its classification results entirely dependent on the provided prompts. Therefore, we focus on generating prompts with more accurate localization and classification and propose \textbf{APSeg}, \textbf{A}uto-\textbf{P}rompt model with acquired and injected knowledge for nuclear instance \textbf{Seg}mentation and classification. APSeg incorporates two knowledge-aware modules: (1) Distribution-Guided Proposal Offset Module (\textbf{DG-POM}), which learns distribution knowledge through density map guided, and (2) Category Knowledge Semantic Injection Module (\textbf{CK-SIM}), which injects morphological knowledge derived from category descriptions. We conducted extensive experiments on the PanNuke and CoNSeP datasets, demonstrating the effectiveness of our approach. The code will be released upon acceptance.
Authors: YiMing Yu, Jason Zutty
Abstract: In machine learning, Neural Architecture Search (NAS) requires domain knowledge of model design and a large amount of trial-and-error to achieve promising performance. Meanwhile, evolutionary algorithms have traditionally relied on fixed rules and pre-defined building blocks. The Large Language Model (LLM)-Guided Evolution (GE) framework transformed this approach by incorporating LLMs to directly modify model source code for image classification algorithms on CIFAR data and intelligently guide mutations and crossovers. A key element of LLM-GE is the "Evolution of Thought" (EoT) technique, which establishes feedback loops, allowing LLMs to refine their decisions iteratively based on how previous operations performed. In this study, we perform NAS for object detection by improving LLM-GE to modify the architecture of You Only Look Once (YOLO) models to enhance performance on the KITTI dataset. Our approach intelligently adjusts the design and settings of YOLO to find the optimal algorithms against objective such as detection accuracy and speed. We show that LLM-GE produced variants with significant performance improvements, such as an increase in Mean Average Precision from 92.5% to 94.5%. This result highlights the flexibility and effectiveness of LLM-GE on real-world challenges, offering a novel paradigm for automated machine learning that combines LLM-driven reasoning with evolutionary strategies.
Authors: Seif Mzoughi, Ahmed Hajyahmed, Mohamed Elshafei, Foutse Khomh anb Diego Elias Costa
Abstract: Deep Learning (DL) systems are increasingly deployed in safety-critical applications, yet they remain vulnerable to robustness issues that can lead to significant failures. While numerous Test Input Generators (TIGs) have been developed to evaluate DL robustness, a comprehensive assessment of their effectiveness across different dimensions is still lacking. This paper presents a comprehensive assessment of four state-of-the-art TIGs--DeepHunter, DeepFault, AdvGAN, and SinVAD--across multiple critical aspects: fault-revealing capability, naturalness, diversity, and efficiency. Our empirical study leverages three pre-trained models (LeNet-5, VGG16, and EfficientNetB3) on datasets of varying complexity (MNIST, CIFAR-10, and ImageNet-1K) to evaluate TIG performance. Our findings reveal important trade-offs in robustness revealing capability, variation in test case generation, and computational efficiency across TIGs. The results also show that TIG performance varies significantly with dataset complexity, as tools that perform well on simpler datasets may struggle with more complex ones. In contrast, others maintain steadier performance or better scalability. This paper offers practical guidance for selecting appropriate TIGs aligned with specific objectives and dataset characteristics. Nonetheless, more work is needed to address TIG limitations and advance TIGs for real-world, safety-critical systems.
Authors: Boris Sukhovilov
Abstract: We propose a novel method for determining the radius of a spherical surface based on the distances measured between points on this surface. We consider the most general case of determining the radius when the distances are measured with errors and the sphere has random deviations from its ideal shape. For the solution, we used the minimally necessary four points and an arbitrary N number of points. We provide a new closed form solution for the radius of the sphere through the matrix of pairwise distances. We also determine the standard deviation of the radius estimate caused by measurement errors and deviations of the sphere from its ideal shape. We found optimal configurations of points on the sphere that provide the minimum standard deviation of the radius estimate. This paper describes our solution and provides all the mathematical derivations. We share the implementation of our method as open source code at https://github.com/boris-sukhovilov/Sphere_Radius.
Authors: Takahiro Shirakawa, Tomoyuki Suzuki, Daichi Haraguchi
Abstract: General image-to-video generation methods often produce suboptimal animations that do not meet the requirements of animated graphics, as they lack active text motion and exhibit object distortion. Also, code-based animation generation methods typically require layer-structured vector data which are often not readily available for motion graphic generation. To address these challenges, we propose a novel framework named MG-Gen that reconstructs data in vector format from a single raster image to extend the capabilities of code-based methods to enable motion graphics generation from a raster image in the framework of general image-to-video generation. MG-Gen first decomposes the input image into layer-wise elements, reconstructs them as HTML format data and then generates executable JavaScript code for the reconstructed HTML data. We experimentally confirm that \ours{} generates motion graphics while preserving text readability and input consistency. These successful results indicate that combining layer decomposition and animation code generation is an effective strategy for motion graphics generation.
Authors: Hantang Li, Jinhua Hao, Lei Xiong, Shuyuan Zhu
Abstract: In practical applications, conventional methods generate large volumes of low-light images that require compression for efficient storage and transmission. However, most existing methods either disregard the removal of potential compression artifacts during the enhancement process or fail to establish a unified framework for joint task enhancement of images with varying compression qualities. To solve this problem, we propose the hybrid priors-guided network (HPGN), which enhances compressed low-light images by integrating both compression and illumination priors. Our approach fully utilizes the JPEG quality factor (QF) and DCT quantization matrix (QM) to guide the design of efficient joint task plug-and-play modules. Additionally, we employ a random QF generation strategy to guide model training, enabling a single model to enhance images across different compression levels. Experimental results confirm the superiority of our proposed method.
Authors: Yudi Sang, Yanzhen Liu, Sutuke Yibulayimu, Yunning Wang, Benjamin D. Killeen, Mingxu Liu, Ping-Cheng Ku, Ole Johannsen, Karol Gotkowski, Maximilian Zenk, Klaus Maier-Hein, Fabian Isensee, Peiyan Yue, Yi Wang, Haidong Yu, Zhaohong Pan, Yutong He, Xiaokun Liang, Daiqi Liu, Fuxin Fan, Artur Jurgas, Andrzej Skalski, Yuxi Ma, Jing Yang, Szymon P{\l}otka, Rafa{\l} Litka, Gang Zhu, Yingchun Song, Mathias Unberath, Mehran Armand, Dan Ruan, S. Kevin Zhou, Qiyong Cao, Chunpeng Zhao, Xinbao Wu, Yu Wang
Abstract: The segmentation of pelvic fracture fragments in CT and X-ray images is crucial for trauma diagnosis, surgical planning, and intraoperative guidance. However, accurately and efficiently delineating the bone fragments remains a significant challenge due to complex anatomy and imaging limitations. The PENGWIN challenge, organized as a MICCAI 2024 satellite event, aimed to advance automated fracture segmentation by benchmarking state-of-the-art algorithms on these complex tasks. A diverse dataset of 150 CT scans was collected from multiple clinical centers, and a large set of simulated X-ray images was generated using the DeepDRR method. Final submissions from 16 teams worldwide were evaluated under a rigorous multi-metric testing scheme. The top-performing CT algorithm achieved an average fragment-wise intersection over union (IoU) of 0.930, demonstrating satisfactory accuracy. However, in the X-ray task, the best algorithm attained an IoU of 0.774, highlighting the greater challenges posed by overlapping anatomical structures. Beyond the quantitative evaluation, the challenge revealed methodological diversity in algorithm design. Variations in instance representation, such as primary-secondary classification versus boundary-core separation, led to differing segmentation strategies. Despite promising results, the challenge also exposed inherent uncertainties in fragment definition, particularly in cases of incomplete fractures. These findings suggest that interactive segmentation approaches, integrating human decision-making with task-relevant information, may be essential for improving model reliability and clinical applicability.
Authors: Naomi Silverstein, Efrat Leibowitz, Ron Beloosesky, Haim Azhari
Abstract: Ultrasound is a widely accessible and cost-effective medical imaging tool commonly used for prenatal evaluation of the fetal brain. However, it has limitations, particularly in the third trimester, where the complexity of the fetal brain requires high image quality for extracting quantitative data. In contrast, magnetic resonance imaging (MRI) offers superior image quality and tissue differentiation but is less available, expensive, and requires time-consuming acquisition. Thus, transforming ultrasonic images into an MRI-mimicking display may be advantageous and allow better tissue anatomy presentation. To address this goal, we have examined the use of artificial intelligence, implementing a diffusion model renowned for generating high-quality images. The proposed method, termed "Dual Diffusion Imposed Correlation" (DDIC), leverages a diffusion-based translation methodology, assuming a shared latent space between ultrasound and MRI domains. Model training was obtained utilizing the "HC18" dataset for ultrasound and the "CRL fetal brain atlas" along with the "FeTA " datasets for MRI. The generated pseudo-MRI images provide notable improvements in visual discrimination of brain tissue, especially in the lateral ventricles and the Sylvian fissure, characterized by enhanced contrast clarity. Improvement was demonstrated in Mutual information, Peak signal-to-noise ratio, Fr\'echet Inception Distance, and Contrast-to-noise ratio. Findings from these evaluations indicate statistically significant superior performance of the DDIC compared to other translation methodologies. In addition, a Medical Opinion Test was obtained from 5 gynecologists. The results demonstrated display improvement in 81% of the tested images. In conclusion, the presented pseudo-MRI images hold the potential for streamlining diagnosis and enhancing clinical outcomes through improved representation.
Authors: Jack Sander, Giammarco Caroleo, Alessandro Albini, Perla Maiolino
Abstract: Tracking motions of humans or objects in the surroundings of the robot is essential to improve safe robot motions and reactions. In this work, we present an approach for scene flow estimation from low-density and noisy point clouds acquired from miniaturized Time of Flight (ToF) sensors distributed on the robot body. The proposed method clusters points from consecutive frames and applies Iterative Closest Point (ICP) to estimate a dense motion flow, with additional steps introduced to mitigate the impact of sensor noise and low-density data points. Specifically, we employ a fitness-based classification to distinguish between stationary and moving points and an inlier removal strategy to refine geometric correspondences. The proposed approach is validated in an experimental setup where 24 ToF are used to estimate the velocity of an object moving at different controlled speeds. Experimental results show that the method consistently approximates the direction of the motion and its magnitude with an error which is in line with sensor noise.
Authors: Soumyaratna Debnath, Ashish Tiwari, Kaustubh Sadekar, Shanmuganathan Raman
Abstract: Recent advancements in learning-based methods have opened new avenues for exploring and interpreting art forms, such as shadow art, origami, and sketch art, through computational models. One notable visual art form is 3D Anamorphic Art in which an ensemble of arbitrarily shaped 3D objects creates a realistic and meaningful expression when observed from a particular viewpoint and loses its coherence over the other viewpoints. In this work, we build on insights from 3D Anamorphic Art to perform 3D object arrangement. We introduce RASP, a differentiable-rendering-based framework to arrange arbitrarily shaped 3D objects within a bounded volume via shadow (or silhouette)-guided optimization with an aim of minimal inter-object spacing and near-maximal occupancy. Furthermore, we propose a novel SDF-based formulation to handle inter-object intersection and container extrusion. We demonstrate that RASP can be extended to part assembly alongside object packing considering 3D objects to be "parts" of another 3D object. Finally, we present artistic illustrations of multi-view anamorphic art, achieving meaningful expressions from multiple viewpoints within a single ensemble.
Authors: Rick van Essen, Eldert van Henten, Lammert Kooistra, Gert Kootstra
Abstract: This paper presents an adaptive path planner for object search in agricultural fields using UAVs. The path planner uses a high-altitude coverage flight path and plans additional low-altitude inspections when the detection network is uncertain. The path planner was evaluated in an offline simulation environment containing real-world images. We trained a YOLOv8 detection network to detect artificial plants placed in grass fields to showcase the potential of our path planner. We evaluated the effect of different detection certainty measures, optimized the path planning parameters, investigated the effects of localization errors and different numbers of objects in the field. The YOLOv8 detection confidence worked best to differentiate between true and false positive detections and was therefore used in the adaptive planner. The optimal parameters of the path planner depended on the distribution of objects in the field, when the objects were uniformly distributed, more low-altitude inspections were needed compared to a non-uniform distribution of objects, resulting in a longer path length. The adaptive planner proved to be robust against localization uncertainty. When increasing the number of objects, the flight path length increased, especially when the objects were uniformly distributed. When the objects were non-uniformly distributed, the adaptive path planner yielded a shorter path than a low-altitude coverage path, even with high number of objects. Overall, the presented adaptive path planner allowed to find non-uniformly distributed objects in a field faster than a coverage path planner and resulted in a compatible detection accuracy. The path planner is made available at https://github.com/wur-abe/uav_adaptive_planner.
Authors: Xiaofeng Han, Shunpeng Chen, Zenghuang Fu, Zhe Feng, Lue Fan, Dong An, Changwei Wang, Li Guo, Weiliang Meng, Xiaopeng Zhang, Rongtao Xu, Shibiao Xu
Abstract: Robot vision has greatly benefited from advancements in multimodal fusion techniques and vision-language models (VLMs). We systematically review the applications of multimodal fusion in key robotic vision tasks, including semantic scene understanding, simultaneous localization and mapping (SLAM), 3D object detection, navigation and localization, and robot manipulation. We compare VLMs based on large language models (LLMs) with traditional multimodal fusion methods, analyzing their advantages, limitations, and synergies. Additionally, we conduct an in-depth analysis of commonly used datasets, evaluating their applicability and challenges in real-world robotic scenarios. Furthermore, we identify critical research challenges such as cross-modal alignment, efficient fusion strategies, real-time deployment, and domain adaptation, and propose future research directions, including self-supervised learning for robust multimodal representations, transformer-based fusion architectures, and scalable multimodal frameworks. Through a comprehensive review, comparative analysis, and forward-looking discussion, we provide a valuable reference for advancing multimodal perception and interaction in robotic vision. A comprehensive list of studies in this survey is available at https://github.com/Xiaofeng-Han-Res/MF-RV.
Authors: Yan Ma, Steffi Chern, Xuyang Shen, Yiran Zhong, Pengfei Liu
Abstract: Reinforcement learning (RL) has recently shown strong potential in improving the reasoning capabilities of large language models and is now being actively extended to vision-language models (VLMs). However, existing RL applications in VLMs often rely on heavily engineered frameworks that hinder reproducibility and accessibility, while lacking standardized evaluation protocols, making it difficult to compare results or interpret training dynamics. This work introduces a transparent, from-scratch framework for RL in VLMs, offering a minimal yet functional four-step pipeline validated across multiple models and datasets. In addition, a standardized evaluation scheme is proposed to assess training dynamics and reflective behaviors. Extensive experiments on visual reasoning tasks uncover key empirical findings: response length is sensitive to random seeds, reflection correlates with output length, and RL consistently outperforms supervised fine-tuning (SFT) in generalization, even with high-quality data. These findings, together with the proposed framework, aim to establish a reproducible baseline and support broader engagement in RL-based VLM research.
Authors: Leonardo Iurada, Marco Ciccone, Tatiana Tommasi
Abstract: Task arithmetic has emerged as a promising approach for editing models by representing task-specific knowledge as composable task vectors. However, existing methods rely on network linearization to derive task vectors, leading to computational bottlenecks during training and inference. Moreover, linearization alone does not ensure weight disentanglement, the key property that enables conflict-free composition of task vectors. To address this, we propose TaLoS which allows to build sparse task vectors with minimal interference without requiring explicit linearization and sharing information across tasks. We find that pre-trained models contain a subset of parameters with consistently low gradient sensitivity across tasks, and that sparsely updating only these parameters allows for promoting weight disentanglement during fine-tuning. Our experiments prove that TaLoS improves training and inference efficiency while outperforming current methods in task addition and negation. By enabling modular parameter editing, our approach fosters practical deployment of adaptable foundation models in real-world applications.
Authors: Chu Han, Bingchao Zhao, Jiatai Lin, Shanshan Lyu, Longfei Wang, Tianpeng Deng, Cheng Lu, Changhong Liang, Hannah Y. Wen, Xiaojing Guo, Zhenwei Shi, Zaiyi Liu
Abstract: Despite the impressive performance across a wide range of applications, current computational pathology models face significant diagnostic efficiency challenges due to their reliance on high-magnification whole-slide image analysis. This limitation severely compromises their clinical utility, especially in time-sensitive diagnostic scenarios and situations requiring efficient data transfer. To address these issues, we present a novel computation- and communication-efficient framework called Magnification-Aligned Global-Local Transformer (MAGA-GLTrans). Our approach significantly reduces computational time, file transfer requirements, and storage overhead by enabling effective analysis using low-magnification inputs rather than high-magnification ones. The key innovation lies in our proposed magnification alignment (MAGA) mechanism, which employs self-supervised learning to bridge the information gap between low and high magnification levels by effectively aligning their feature representations. Through extensive evaluation across various fundamental CPath tasks, MAGA-GLTrans demonstrates state-of-the-art classification performance while achieving remarkable efficiency gains: up to 10.7 times reduction in computational time and over 20 times reduction in file transfer and storage requirements. Furthermore, we highlight the versatility of our MAGA framework through two significant extensions: (1) its applicability as a feature extractor to enhance the efficiency of any CPath architecture, and (2) its compatibility with existing foundation models and histopathology-specific encoders, enabling them to process low-magnification inputs with minimal information loss. These advancements position MAGA-GLTrans as a particularly promising solution for time-sensitive applications, especially in the context of intraoperative frozen section diagnosis where both accuracy and efficiency are paramount.
Authors: Feng Gao, Miao Fu, Jingchao Cao, Junyu Dong, Qian Du
Abstract: Semantic segmentation of high-resolution remote sensing images plays a crucial role in land-use monitoring and urban planning. Recent remarkable progress in deep learning-based methods makes it possible to generate satisfactory segmentation results. However, existing methods still face challenges in adapting network parameters to various land cover distributions and enhancing the interaction between spatial and frequency domain features. To address these challenges, we propose the Adaptive Frequency Enhancement Network (AFENet), which integrates two key components: the Adaptive Frequency and Spatial feature Interaction Module (AFSIM) and the Selective feature Fusion Module (SFM). AFSIM dynamically separates and modulates high- and low-frequency features according to the content of the input image. It adaptively generates two masks to separate high- and low-frequency components, therefore providing optimal details and contextual supplementary information for ground object feature representation. SFM selectively fuses global context and local detailed features to enhance the network's representation capability. Hence, the interactions between frequency and spatial features are further enhanced. Extensive experiments on three publicly available datasets demonstrate that the proposed AFENet outperforms state-of-the-art methods. In addition, we also validate the effectiveness of AFSIM and SFM in managing diverse land cover types and complex scenarios. Our codes are available at https://github.com/oucailab/AFENet.
Authors: Mei Li, Yuxiang Lu, Qinyan Dai, Suizhi Huang, Yue Ding, Hongtao Lu
Abstract: Continual Learning (CL) strives to learn incrementally across tasks while mitigating catastrophic forgetting. A key challenge in CL is balancing stability (retaining prior knowledge) and plasticity (learning new tasks). While representative gradient projection methods ensure stability, they often limit plasticity. Model merging techniques offer promising solutions, but prior methods typically rely on empirical assumptions and carefully selected hyperparameters. In this paper, we explore the potential of model merging to enhance the stability-plasticity trade-off, providing theoretical insights that underscore its benefits. Specifically, we reformulate the merging mechanism using Bayesian continual learning principles and derive a closed-form solution for the optimal merging coefficient that adapts to the diverse characteristics of tasks. To validate our approach, we introduce a two-stage framework named BECAME, which synergizes the expertise of gradient projection and adaptive merging. Extensive experiments show that our approach outperforms state-of-the-art CL methods and existing merging strategies.
Authors: Prashanth Chandran, Agon Serifi, Markus Gross, Moritz B\"acher
Abstract: We introduce Spline-based Transformers, a novel class of Transformer models that eliminate the need for positional encoding. Inspired by workflows using splines in computer animation, our Spline-based Transformers embed an input sequence of elements as a smooth trajectory in latent space. Overcoming drawbacks of positional encoding such as sequence length extrapolation, Spline-based Transformers also provide a novel way for users to interact with transformer latent spaces by directly manipulating the latent control points to create new latent trajectories and sequences. We demonstrate the superior performance of our approach in comparison to conventional positional encoding on a variety of datasets, ranging from synthetic 2D to large-scale real-world datasets of images, 3D shapes, and animations.
Authors: Jiawen Zhu, Xin Chen, Haiwen Diao, Shuai Li, Jun-Yan He, Chenyang Li, Bin Luo, Dong Wang, Huchuan Lu
Abstract: The speed-precision trade-off is a critical problem for visual object tracking which usually requires low latency and deployment on constrained resources. Existing solutions for efficient tracking mainly focus on adopting light-weight backbones or modules, which nevertheless come at the cost of a sacrifice in precision. In this paper, inspired by dynamic network routing, we propose DyTrack, a dynamic transformer framework for efficient tracking. Real-world tracking scenarios exhibit diverse levels of complexity. We argue that a simple network is sufficient for easy frames in video sequences, while more computation could be assigned to difficult ones. DyTrack automatically learns to configure proper reasoning routes for various inputs, gaining better utilization of the available computational budget. Thus, it can achieve higher performance with the same running speed. We formulate instance-specific tracking as a sequential decision problem and attach terminating branches to intermediate layers of the entire model. Especially, to fully utilize the computations, we introduce the feature recycling mechanism to reuse the outputs of predecessors. Furthermore, a target-aware self-distillation strategy is designed to enhance the discriminating capabilities of early predictions by effectively mimicking the representation pattern of the deep model. Extensive experiments on multiple benchmarks demonstrate that DyTrack achieves promising speed-precision trade-offs with only a single model. For instance, DyTrack obtains 64.9% AUC on LaSOT with a speed of 256 fps.
Authors: Lifan Jiang, Zhihui Wang, Changmiao Wang, Ming Li, Jiaxu Leng
Abstract: Object detection, a quintessential task in the realm of perceptual computing, can be tackled using a generative methodology. In the present study, we introduce a novel framework designed to articulate object detection as a denoising diffusion process, which operates on the perturbed bounding boxes of annotated entities. This framework, termed \textbf{ConsistencyDet}, leverages an innovative denoising concept known as the Consistency Model. The hallmark of this model is its self-consistency feature, which empowers the model to map distorted information from any time step back to its pristine state, thereby realizing a \textbf{``few-step denoising''} mechanism. Such an attribute markedly elevates the operational efficiency of the model, setting it apart from the conventional Diffusion Model. Throughout the training phase, ConsistencyDet initiates the diffusion sequence with noise-infused boxes derived from the ground-truth annotations and conditions the model to perform the denoising task. Subsequently, in the inference stage, the model employs a denoising sampling strategy that commences with bounding boxes randomly sampled from a normal distribution. Through iterative refinement, the model transforms an assortment of arbitrarily generated boxes into definitive detections. Comprehensive evaluations employing standard benchmarks, such as MS-COCO and LVIS, corroborate that ConsistencyDet surpasses other leading-edge detectors in performance metrics. Our code is available at https://anonymous.4open.science/r/ConsistencyDet-37D5.
URLs: https://anonymous.4open.science/r/ConsistencyDet-37D5.
Authors: Runqi Wang, Caoyuan Ma, Guopeng Li, Hanrui Xu, Yuke Li, Zheng Wang
Abstract: Text to Motion aims to generate human motions from texts. Existing settings rely on limited Action Texts that include action labels, which limits flexibility and practicability in scenarios difficult to describe directly. This paper extends limited Action Texts to arbitrary ones. Scene texts without explicit action labels can enhance the practicality of models in complex and diverse industries such as virtual human interaction, robot behavior generation, and film production, while also supporting the exploration of potential implicit behavior patterns. However, newly introduced Scene Texts may yield multiple reasonable output results, causing significant challenges in existing data, framework, and evaluation. To address this practical issue, we first create a new dataset HUMANML3D++ by extending texts of the largest existing dataset HUMANML3D. Secondly, we propose a simple yet effective framework that extracts action instructions from arbitrary texts and subsequently generates motions. Furthermore, we also benchmark this new setting with multi-solution metrics to address the inadequacies of existing single-solution metrics. Extensive experiments indicate that Text to Motion in this realistic setting is challenging, fostering new research in this practical direction.
Authors: Prannay Kaul, Zhizhong Li, Hao Yang, Yonatan Dukler, Ashwin Swaminathan, C. J. Taylor, Stefano Soatto
Abstract: Mitigating hallucinations in large vision-language models (LVLMs) remains an open problem. Recent benchmarks do not address hallucinations in open-ended free-form responses, which we term "Type I hallucinations". Instead, they focus on hallucinations responding to very specific question formats -- typically a multiple-choice response regarding a particular object or attribute -- which we term "Type II hallucinations". Additionally, such benchmarks often require external API calls to models which are subject to change. In practice, we observe that a reduction in Type II hallucinations does not lead to a reduction in Type I hallucinations but rather that the two forms of hallucinations are often anti-correlated. To address this, we propose THRONE, a novel object-based automatic framework for quantitatively evaluating Type I hallucinations in LVLM free-form outputs. We use public language models (LMs) to identify hallucinations in LVLM responses and compute informative metrics. By evaluating a large selection of recent LVLMs using public datasets, we show that an improvement in existing metrics do not lead to a reduction in Type I hallucinations, and that established benchmarks for measuring Type I hallucinations are incomplete. Finally, we provide a simple and effective data augmentation method to reduce Type I and Type II hallucinations as a strong baseline. Code is now available at https://github.com/amazon-science/THRONE .
Authors: Jing Liu, Yang Liu, Jieyu Lin, Jielin Li, Liang Cao, Peng Sun, Bo Hu, Liang Song, Azzedine Boukerche, Victor C. M. Leung
Abstract: The increasing utilization of surveillance cameras in smart cities, coupled with the surge of online video applications, has heightened concerns regarding public security and privacy protection, which propelled automated Video Anomaly Detection (VAD) into a fundamental research task within the Artificial Intelligence (AI) community. With the advancements in deep learning and edge computing, VAD has made significant progress and advances synergized with emerging applications in smart cities and video internet, which has moved beyond the conventional research scope of algorithm engineering to deployable Networking Systems for VAD (NSVAD), a practical hotspot for intersection exploration in the AI, IoVT, and computing fields. In this article, we delineate the foundational assumptions, learning frameworks, and applicable scenarios of various deep learning-driven VAD routes, offering an exhaustive tutorial for novices in NSVAD. In addition, this article elucidates core concepts by reviewing recent advances and typical solutions and aggregating available research resources accessible at https://github.com/fdjingliu/NSVAD. Lastly, this article projects future development trends and discusses how the integration of AI and computing technologies can address existing research challenges and promote open opportunities, serving as an insightful guide for prospective researchers and engineers.
Authors: Hanrong Zhang, Zhenting Wang, Boheng Li, Fulin Lin, Tingxu Han, Mingyu Jin, Chenlu Zhan, Mengnan Du, Hongwei Wang, Shiqing Ma
Abstract: Self-supervised learning (SSL) models are vulnerable to backdoor attacks. Existing backdoor attacks that are effective in SSL often involve noticeable triggers, like colored patches or visible noise, which are vulnerable to human inspection. This paper proposes an imperceptible and effective backdoor attack against self-supervised models. We first find that existing imperceptible triggers designed for supervised learning are less effective in compromising self-supervised models. We then identify this ineffectiveness is attributed to the overlap in distributions between the backdoor and augmented samples used in SSL. Building on this insight, we design an attack using optimized triggers disentangled with the augmented transformation in the SSL, while remaining imperceptible to human vision. Experiments on five datasets and six SSL algorithms demonstrate our attack is highly effective and stealthy. It also has strong resistance to existing backdoor defenses. Our code can be found at https://github.com/Zhang-Henry/INACTIVE.
Authors: Hastings Greer, Lin Tian, Francois-Xavier Vialard, Roland Kwitt, Raul San Jose Estepar, Marc Niethammer
Abstract: Image registration estimates spatial correspondences between a pair of images. These estimates are typically obtained via numerical optimization or regression by a deep network. A desirable property of such estimators is that a correspondence estimate (e.g., the true oracle correspondence) for an image pair is maintained under deformations of the input images. Formally, the estimator should be equivariant to a desired class of image transformations. In this work, we present careful analyses of the desired equivariance properties in the context of multi-step deep registration networks. Based on these analyses we 1) introduce the notions of $[U,U]$ equivariance (network equivariance to the same deformations of the input images) and $[W,U]$ equivariance (where input images can undergo different deformations); we 2) show that in a suitable multi-step registration setup it is sufficient for overall $[W,U]$ equivariance if the first step has $[W,U]$ equivariance and all others have $[U,U]$ equivariance; we 3) show that common displacement-predicting networks only exhibit $[U,U]$ equivariance to translations instead of the more powerful $[W,U]$ equivariance; and we 4) show how to achieve multi-step $[W,U]$ equivariance via a coordinate-attention mechanism combined with displacement-predicting refinement layers (CARL). Overall, our approach obtains excellent practical registration performance on several 3D medical image registration tasks and outperforms existing unsupervised approaches for the challenging problem of abdomen registration.
Authors: Khiem Le, Zhichun Guo, Kaiwen Dong, Xiaobao Huang, Bozhao Nan, Roshni Iyer, Xiangliang Zhang, Olaf Wiest, Wei Wang, Nitesh V. Chawla
Abstract: Large Language Models (LLMs) with their strong task-handling capabilities have shown remarkable advancements across a spectrum of fields, moving beyond natural language understanding. However, their proficiency within the chemistry domain remains restricted, especially in solving professional molecule-related tasks. This challenge is attributed to their inherent limitations in comprehending molecules using only common textual representations, i.e., SMILES strings. In this study, we seek to enhance the ability of LLMs to comprehend molecules by equipping them with a multi-modal external module, namely MolX. In particular, instead of directly using a SMILES string to represent a molecule, we utilize specific encoders to extract fine-grained features from both SMILES string and 2D molecular graph representations for feeding into an LLM. Moreover, a handcrafted molecular fingerprint is incorporated to leverage its embedded domain knowledge. Then, to establish an alignment between MolX and the LLM's textual input space, the whole model in which the LLM is frozen, is pre-trained with a versatile strategy including a diverse set of tasks. Experimental evaluations show that our proposed method outperforms baselines across 4 downstream molecule-related tasks ranging from molecule-to-text translation to retrosynthesis, with and without fine-tuning the LLM, while only introducing a small number of trainable parameters 0.53% and 0.82%, respectively.
Authors: Ping Liu, Qiqi Tao, Joey Tianyi Zhou
Abstract: As synthetic media, including video, audio, and text, become increasingly indistinguishable from real content, the risks of misinformation, identity fraud, and social manipulation escalate. This survey traces the evolution of deepfake detection from early single-modal methods to sophisticated multi-modal approaches that integrate audio-visual and text-visual cues. We present a structured taxonomy of detection techniques and analyze the transition from GAN-based to diffusion model-driven deepfakes, which introduce new challenges due to their heightened realism and robustness against detection. Unlike prior surveys that primarily focus on single-modal detection or earlier deepfake techniques, this work provides the most comprehensive study to date, encompassing the latest advancements in multi-modal deepfake detection, generalization challenges, proactive defense mechanisms, and emerging datasets specifically designed to support new interpretability and reasoning tasks. We further explore the role of Vision-Language Models (VLMs) and Multimodal Large Language Models (MLLMs) in strengthening detection robustness against increasingly sophisticated deepfake attacks. By systematically categorizing existing methods and identifying emerging research directions, this survey serves as a foundation for future advancements in combating AI-generated facial forgeries. A curated list of all related papers can be found at \href{https://github.com/qiqitao77/Comprehensive-Advances-in-Deepfake-Detection-Spanning-Diverse-Modalities}{https://github.com/qiqitao77/Awesome-Comprehensive-Deepfake-Detection}.
URLs: https://github.com/qiqitao77/Comprehensive-Advances-in-Deepfake-Detection-Spanning-Diverse-Modalities, https://github.com/qiqitao77/Awesome-Comprehensive-Deepfake-Detection
Authors: Moshe Kimhi, Omer Kerem, Eden Grad, Ehud Rivlin, Chaim Baskin
Abstract: Obtaining accurate labels for instance segmentation is particularly challenging due to the complex nature of the task. Each image necessitates multiple annotations, encompassing not only the object class but also its precise spatial boundaries. These requirements elevate the likelihood of errors and inconsistencies in both manual and automated annotation processes. By simulating different noise conditions, we provide a realistic scenario for assessing the robustness and generalization capabilities of instance segmentation models in different segmentation tasks, introducing COCO-N and Cityscapes-N. We also propose a benchmark for weakly annotation noise, dubbed COCO-WAN, which utilizes foundation models and weak annotations to simulate semi-automated annotation tools and their noisy labels. This study sheds light on the quality of segmentation masks produced by various models and challenges the efficacy of popular methods designed to address learning with label noise.
Authors: Khoi Nguyen Tiet Nguyen, Wenyu Zhang, Kangkang Lu, Yuhuan Wu, Xingjian Zheng, Hui Li Tan, Liangli Zhen
Abstract: Deep learning models achieve remarkable accuracy in computer vision tasks, yet remain vulnerable to adversarial examples--carefully crafted perturbations to input images that can deceive these models into making confident but incorrect predictions. This vulnerability pose significant risks in high-stakes applications such as autonomous vehicles, security surveillance, and safety-critical inspection systems. While the existing literature extensively covers adversarial attacks in image classification, comprehensive analyses of such attacks on object detection systems remain limited. This paper presents a novel taxonomic framework for categorizing adversarial attacks specific to object detection architectures, synthesizes existing robustness metrics, and provides a comprehensive empirical evaluation of state-of-the-art attack methodologies on popular object detection models, including both traditional detectors and modern detectors with vision-language pretraining. Through rigorous analysis of open-source attack implementations and their effectiveness across diverse detection architectures, we derive key insights into attack characteristics. Furthermore, we delineate critical research gaps and emerging challenges to guide future investigations in securing object detection systems against adversarial threats. Our findings establish a foundation for developing more robust detection models while highlighting the urgent need for standardized evaluation protocols in this rapidly evolving domain.
Authors: Corentin Dumery, Aoxiang Fan, Ren Li, Nicolas Talabot, Pascal Fua
Abstract: Radiance Fields have become a powerful tool for modeling 3D scenes from multiple images. However, they remain difficult to segment into semantically meaningful regions. Some methods work well using 2D semantic masks, but they generalize poorly to class-agnostic segmentations. More recent methods circumvent this issue by using contrastive learning to optimize a high-dimensional 3D feature field instead. However, recovering a segmentation then requires clustering and fine-tuning the associated hyperparameters. In contrast, we aim to identify the necessary changes in segmentation field methods to directly learn a segmentation field while being robust to inconsistent class-agnostic masks, successfully decomposing the scene into a set of objects of any class. By introducing an additional spatial regularization term and restricting the field to a limited number of competing object slots against which masks are matched, a meaningful object representation emerges that best explains the 2D supervision. Our experiments demonstrate the ability of our method to generate 3D panoptic segmentations on complex scenes, and extract high-quality 3D assets from radiance fields that can then be used in virtual 3D environments.
Authors: Chongkai Yu, Ting Liu, Anqi Li, Xiaochao Qu, Chengjing Wu, Luoqi Liu, Xiaolin Hu
Abstract: Interactive segmentation is to segment the mask of the target object according to the user's interactive prompts. There are two mainstream strategies: early fusion and late fusion. Current specialist models utilize the early fusion strategy that encodes the combination of images and prompts to target the prompted objects, yet repetitive complex computations on the images result in high latency. Late fusion models extract image embeddings once and merge them with the prompts in later interactions. This strategy avoids redundant image feature extraction and improves efficiency significantly. A recent milestone is the Segment Anything Model (SAM). However, this strategy limits the models' ability to extract detailed information from the prompted target zone. To address this issue, we propose SAM-REF, a two-stage refinement framework that fully integrates images and prompts by using a lightweight refiner into the interaction of late fusion, which combines the accuracy of early fusion and maintains the efficiency of late fusion. Through extensive experiments, we show that our SAM-REF model outperforms the current state-of-the-art method in most metrics on segmentation quality without compromising efficiency.
Authors: Shehreen Azad, Yash Jain, Rishit Garg, Yogesh S Rawat, Vibhav Vineet
Abstract: Geometric understanding - including depth and height perception - is fundamental to intelligence and crucial for navigating our environment. Despite the impressive capabilities of large Vision Language Models (VLMs), it remains unclear how well they possess the geometric understanding required for practical applications in visual perception. In this work, we focus on evaluating the geometric understanding of these models, specifically targeting their ability to perceive the depth and height of objects in an image. To address this, we introduce GeoMeter, a suite of benchmark datasets - encompassing 2D and 3D scenarios - to rigorously evaluate these aspects. By benchmarking 18 state-of-the-art VLMs, we found that although they excel in perceiving basic geometric properties like shape and size, they consistently struggle with depth and height perception. Our analysis reveal that these challenges stem from shortcomings in their depth and height reasoning capabilities and inherent biases. This study aims to pave the way for developing VLMs with enhanced geometric understanding by emphasizing depth and height perception as critical components necessary for real-world applications.
Authors: Shashank Tripathi, Omid Taheri, Christoph Lassner, Michael J. Black, Daniel Holden, Carsten Stoll
Abstract: Generating realistic human motion is essential for many computer vision and graphics applications. The wide variety of human body shapes and sizes greatly impacts how people move. However, most existing motion models ignore these differences, relying on a standardized, average body. This leads to uniform motion across different body types, where movements don't match their physical characteristics, limiting diversity. To solve this, we introduce a new approach to develop a generative motion model based on body shape. We show that it's possible to train this model using unpaired data by applying cycle consistency, intuitive physics, and stability constraints, which capture the relationship between identity and movement. The resulting model generates diverse, physically plausible, and dynamically stable human motions that are both quantitatively and qualitatively more realistic than current state-of-the-art methods. More details are available on our project page https://CarstenEpic.github.io/humos/.
Authors: Minmin Yang
Abstract: During the COVID-19 pandemic, face masks have become ubiquitous in our lives. Face masks can cause some face recognition models to fail since they cover significant portion of a face. In addition, removing face masks from captured images or videos can be desirable, e.g., for better social interaction and for image/video editing and enhancement purposes. Hence, we propose a generative face inpainting method to effectively recover/reconstruct the masked part of a face. Face inpainting is more challenging compared to traditional inpainting, since it requires high fidelity while maintaining the identity at the same time. Our proposed method includes a Multi-scale Channel-Spatial Attention Module (M-CSAM) to mitigate the spatial information loss and learn the inter- and intra-channel correlation. In addition, we introduce an approach enforcing the supervised signal to focus on masked regions instead of the whole image. We also synthesize our own Masked-Faces dataset from the CelebA dataset by incorporating five different types of face masks, including surgical mask, regular mask and scarves, which also cover the neck area. The experimental results show that our proposed method outperforms different baselines in terms of structural similarity index measure, peak signal-to-noise ratio and l1 loss, while also providing better outputs qualitatively. The code will be made publicly available. Code is available at GitHub.
Authors: Xiaofeng Mao, Zhengkai Jiang, Fu-Yun Wang, Jiangning Zhang, Hao Chen, Mingmin Chi, Yabiao Wang, Wenhan Luo
Abstract: Video diffusion models have shown great potential in generating high-quality videos, making them an increasingly popular focus. However, their inherent iterative nature leads to substantial computational and time costs. While efforts have been made to accelerate video diffusion by reducing inference steps (through techniques like consistency distillation) and GAN training (these approaches often fall short in either performance or training stability). In this work, we introduce a two-stage training framework that effectively combines consistency distillation with GAN training to address these challenges. Additionally, we propose a novel video discriminator design, which eliminates the need for decoding the video latents and improves the final performance. Our model is capable of producing high-quality videos in merely one-step, with the flexibility to perform multi-step refinement for further performance enhancement. Our quantitative evaluation on the OpenWebVid-1M benchmark shows that our model significantly outperforms existing methods. Notably, our 1-step performance(FVD 171.15) exceeds the 8-step performance of the consistency distillation based method, AnimateLCM (FVD 184.79), and approaches the 25-step performance of advanced Stable Video Diffusion (FVD 156.94).
Authors: Adrian Chan, Anupam Mijar, Mehreen Saeed, Chau-Wai Wong, Akram Khater
Abstract: Arabic handwritten text recognition (HTR) is challenging, especially for historical texts, due to diverse writing styles and the intrinsic features of Arabic script. Additionally, Arabic handwriting datasets are smaller compared to English ones, making it difficult to train generalizable Arabic HTR models. To address these challenges, we propose HATFormer, a transformer-based encoder-decoder architecture that builds on a state-of-the-art English HTR model. By leveraging the transformer's attention mechanism, HATFormer captures spatial contextual information to address the intrinsic challenges of Arabic script through differentiating cursive characters, decomposing visual representations, and identifying diacritics. Our customization to historical handwritten Arabic includes an image processor for effective ViT information preprocessing, a text tokenizer for compact Arabic text representation, and a training pipeline that accounts for a limited amount of historic Arabic handwriting data. HATFormer achieves a character error rate (CER) of 8.6% on the largest public historical handwritten Arabic dataset, with a 51% improvement over the best baseline in the literature. HATFormer also attains a comparable CER of 4.2% on the largest private non-historical dataset. Our work demonstrates the feasibility of adapting an English HTR method to a low-resource language with complex, language-specific challenges, contributing to advancements in document digitization, information retrieval, and cultural preservation.
Authors: Haian Jin, Hanwen Jiang, Hao Tan, Kai Zhang, Sai Bi, Tianyuan Zhang, Fujun Luan, Noah Snavely, Zexiang Xu
Abstract: We propose the Large View Synthesis Model (LVSM), a novel transformer-based approach for scalable and generalizable novel view synthesis from sparse-view inputs. We introduce two architectures: (1) an encoder-decoder LVSM, which encodes input image tokens into a fixed number of 1D latent tokens, functioning as a fully learned scene representation, and decodes novel-view images from them; and (2) a decoder-only LVSM, which directly maps input images to novel-view outputs, completely eliminating intermediate scene representations. Both models bypass the 3D inductive biases used in previous methods -- from 3D representations (e.g., NeRF, 3DGS) to network designs (e.g., epipolar projections, plane sweeps) -- addressing novel view synthesis with a fully data-driven approach. While the encoder-decoder model offers faster inference due to its independent latent representation, the decoder-only LVSM achieves superior quality, scalability, and zero-shot generalization, outperforming previous state-of-the-art methods by 1.5 to 3.5 dB PSNR. Comprehensive evaluations across multiple datasets demonstrate that both LVSM variants achieve state-of-the-art novel view synthesis quality. Notably, our models surpass all previous methods even with reduced computational resources (1-2 GPUs). Please see our website for more details: https://haian-jin.github.io/projects/LVSM/ .
Authors: Liang Mi, Weijun Wang, Wenming Tu, Qingfeng He, Rui Kong, Xinyu Fang, Yazhu Dong, Yikang Zhang, Yunchun Li, Meng Li, Haipeng Dai, Guihai Chen, Yunxin Liu
Abstract: Large Multimodal Models (LMMs) have shown significant progress in various complex vision tasks with the solid linguistic and reasoning capacity inherited from large language models (LMMs). Low-rank adaptation (LoRA) offers a promising method to integrate external knowledge into LMMs, compensating for their limitations on domain-specific tasks. However, the existing LoRA model serving is excessively computationally expensive and causes extremely high latency. In this paper, we present an end-to-end solution that empowers diverse vision tasks and enriches vision applications with LoRA LMMs. Our system, VaLoRA, enables accurate and efficient vision tasks by 1) an accuracy-aware LoRA adapter generation approach that generates LoRA adapters rich in domain-specific knowledge to meet application-specific accuracy requirements, 2) an adaptive-tiling LoRA adapters batching operator that efficiently computes concurrent heterogeneous LoRA adapters, and 3) a flexible LoRA adapter orchestration mechanism that manages application requests and LoRA adapters to achieve the lowest average response latency. We prototype VaLoRA on five popular vision tasks on three LMMs. Experiment results reveal that VaLoRA improves 24-62% of the accuracy compared to the original LMMs and reduces 20-89% of the latency compared to the state-of-the-art LoRA model serving systems.
Authors: Huayang Huang, Yu Wu, Qian Wang
Abstract: Watermarking generative content serves as a vital tool for authentication, ownership protection, and mitigation of potential misuse. Existing watermarking methods face the challenge of balancing robustness and concealment. They empirically inject a watermark that is both invisible and robust and passively achieve concealment by limiting the strength of the watermark, thus reducing the robustness. In this paper, we propose to explicitly introduce a watermark hiding process to actively achieve concealment, thus allowing the embedding of stronger watermarks. To be specific, we implant a robust watermark in an intermediate diffusion state and then guide the model to hide the watermark in the final generated image. We employ an adversarial optimization algorithm to produce the optimal hiding prompt guiding signal for each watermark. The prompt embedding is optimized to minimize artifacts in the generated image, while the watermark is optimized to achieve maximum strength. The watermark can be verified by reversing the generation process. Experiments on various diffusion models demonstrate the watermark remains verifiable even under significant image tampering and shows superior invisibility compared to other state-of-the-art robust watermarking methods. Code is available at https://github.com/Hannah1102/ROBIN.
Authors: Huiwon Jang, Sihyun Yu, Jinwoo Shin, Pieter Abbeel, Younggyo Seo
Abstract: Efficient tokenization of videos remains a challenge in training vision models that can process long videos. One promising direction is to develop a tokenizer that can encode long video clips, as it would enable the tokenizer to leverage the temporal coherence of videos better for tokenization. However, training existing tokenizers on long videos often incurs a huge training cost as they are trained to reconstruct all the frames at once. In this paper, we introduce CoordTok, a video tokenizer that learns a mapping from coordinate-based representations to the corresponding patches of input videos, inspired by recent advances in 3D generative models. In particular, CoordTok encodes a video into factorized triplane representations and reconstructs patches that correspond to randomly sampled $(x,y,t)$ coordinates. This allows for training large tokenizer models directly on long videos without requiring excessive training resources. Our experiments show that CoordTok can drastically reduce the number of tokens for encoding long video clips. For instance, CoordTok can encode a 128-frame video with 128$\times$128 resolution into 1280 tokens, while baselines need 6144 or 8192 tokens to achieve similar reconstruction quality. We further show that this efficient video tokenization enables memory-efficient training of a diffusion transformer that can generate 128 frames at once.
Authors: Yilong Wang, Zilin Gao, Qilong Wang, Zhaofeng Chen, Peihua Li, Qinghua Hu
Abstract: Going beyond few-shot action recognition (FSAR), cross-domain FSAR (CDFSAR) has attracted recent research interests by solving the domain gap lying in source-to-target transfer learning. Existing CDFSAR methods mainly focus on joint training of source and target data to mitigate the side effect of domain gap. However, such kind of methods suffer from two limitations: First, pair-wise joint training requires retraining deep models in case of one source data and multiple target ones, which incurs heavy computation cost, especially for large source and small target data. Second, pre-trained models after joint training are adopted to target domain in a straightforward manner, hardly taking full potential of pre-trained models and then limiting recognition performance. To overcome above limitations, this paper proposes a simple yet effective baseline, namely Temporal-Aware Model Tuning (TAMT) for CDFSAR. Specifically, our TAMT involves a decoupled paradigm by performing pre-training on source data and fine-tuning target data, which avoids retraining for multiple target data with single source. To effectively and efficiently explore the potential of pre-trained models in transferring to target domain, our TAMT proposes a Hierarchical Temporal Tuning Network (HTTN), whose core involves local temporal-aware adapters (TAA) and a global temporal-aware moment tuning (GTMT). Particularly, TAA learns few parameters to recalibrate the intermediate features of frozen pre-trained models, enabling efficient adaptation to target domains. Furthermore, GTMT helps to generate powerful video representations, improving match performance on the target domain. Experiments on several widely used video benchmarks show our TAMT outperforms the recently proposed counterparts by 13%$\sim$31%, achieving new state-of-the-art CDFSAR results.
Authors: Nitish Mital, Simon Malzard, Richard Walters, Celso M. De Melo, Raghuveer Rao, Victoria Nockles
Abstract: Limited real-world data severely impacts model performance in many computer vision domains, particularly for samples that are underrepresented in training. Synthetically generated images are a promising solution, but 1) it remains unclear how to design synthetic training data to optimally improve model performance (e.g, whether and where to introduce more realism or more abstraction) and 2) the domain expertise, time and effort required from human operators for this design and optimisation process represents a major practical challenge. Here we propose a novel conceptual approach to improve the efficiency of designing synthetic images, by using robust Explainable AI (XAI) techniques to guide a human-in-the-loop process of modifying 3D mesh models used to generate these images. Importantly, this framework allows both modifications that increase and decrease realism in synthetic data, which can both improve model performance. We illustrate this concept using a real-world example where data are sparse; detection of vehicles in infrared imagery. We fine-tune an initial YOLOv8 model on the ATR DSIAC infrared dataset and synthetic images generated from 3D mesh models in the Unity gaming engine, and then use XAI saliency maps to guide modification of our Unity models. We show that synthetic data can improve detection of vehicles in orientations unseen in training by 4.6% (to mAP50 = 94.6%). We further improve performance by an additional 1.5% (to 96.1%) through our new XAI-guided approach, which reduces misclassifications through both increasing and decreasing the realism of different parts of the synthetic data. Our proof-of-concept results pave the way for fine, XAI-controlled curation of synthetic datasets tailored to improve object detection performance, whilst simultaneously reducing the burden on human operators in designing and optimising these datasets.
Authors: Yufeng Jin, Vignesh Prasad, Snehal Jauhri, Mathias Franzius, Georgia Chalvatzaki
Abstract: Efficient and accurate object pose estimation is an essential component for modern vision systems in many applications such as Augmented Reality, autonomous driving, and robotics. While research in model-based 6D object pose estimation has delivered promising results, model-free methods are hindered by the high computational load in rendering and inferring consistent poses of arbitrary objects in a live RGB-D video stream. To address this issue, we present 6DOPE-GS, a novel method for online 6D object pose estimation \& tracking with a single RGB-D camera by effectively leveraging advances in Gaussian Splatting. Thanks to the fast differentiable rendering capabilities of Gaussian Splatting, 6DOPE-GS can simultaneously optimize for 6D object poses and 3D object reconstruction. To achieve the necessary efficiency and accuracy for live tracking, our method uses incremental 2D Gaussian Splatting with an intelligent dynamic keyframe selection procedure to achieve high spatial object coverage and prevent erroneous pose updates. We also propose an opacity statistic-based pruning mechanism for adaptive Gaussian density control, to ensure training stability and efficiency. We evaluate our method on the HO3D and YCBInEOAT datasets and show that 6DOPE-GS matches the performance of state-of-the-art baselines for model-free simultaneous 6D pose tracking and reconstruction while providing a 5$\times$ speedup. We also demonstrate the method's suitability for live, dynamic object tracking and reconstruction in a real-world setting.
Authors: Lingchen Sun, Rongyuan Wu, Zhiyuan Ma, Shuaizheng Liu, Qiaosi Yi, Lei Zhang
Abstract: Diffusion prior-based methods have shown impressive results in real-world image super-resolution (SR). However, most existing methods entangle pixel-level and semantic-level SR objectives in the training process, struggling to balance pixel-wise fidelity and perceptual quality. Meanwhile, users have varying preferences on SR results, thus it is demanded to develop an adjustable SR model that can be tailored to different fidelity-perception preferences during inference without re-training. We present Pixel-level and Semantic-level Adjustable SR (PiSA-SR), which learns two LoRA modules upon the pre-trained stable-diffusion (SD) model to achieve improved and adjustable SR results. We first formulate the SD-based SR problem as learning the residual between the low-quality input and the high-quality output, then show that the learning objective can be decoupled into two distinct LoRA weight spaces: one is characterized by the $\ell_2$-loss for pixel-level regression, and another is characterized by the LPIPS and classifier score distillation losses to extract semantic information from pre-trained classification and SD models. In its default setting, PiSA-SR can be performed in a single diffusion step, achieving leading real-world SR results in both quality and efficiency. By introducing two adjustable guidance scales on the two LoRA modules to control the strengths of pixel-wise fidelity and semantic-level details during inference, PiSASR can offer flexible SR results according to user preference without re-training. Codes and models can be found at https://github.com/csslc/PiSA-SR.
Authors: M. Hamza Mughal, Rishabh Dabral, Merel C. J. Scholman, Vera Demberg, Christian Theobalt
Abstract: Non-verbal communication often comprises of semantically rich gestures that help convey the meaning of an utterance. Producing such semantic co-speech gestures has been a major challenge for the existing neural systems that can generate rhythmic beat gestures, but struggle to produce semantically meaningful gestures. Therefore, we present RAG-Gesture, a diffusion-based gesture generation approach that leverages Retrieval Augmented Generation (RAG) to produce natural-looking and semantically rich gestures. Our neuro-explicit gesture generation approach is designed to produce semantic gestures grounded in interpretable linguistic knowledge. We achieve this by using explicit domain knowledge to retrieve exemplar motions from a database of co-speech gestures. Once retrieved, we then inject these semantic exemplar gestures into our diffusion-based gesture generation pipeline using DDIM inversion and retrieval guidance at the inference time without any need of training. Further, we propose a control paradigm for guidance, that allows the users to modulate the amount of influence each retrieval insertion has over the generated sequence. Our comparative evaluations demonstrate the validity of our approach against recent gesture generation approaches. The reader is urged to explore the results on our project page.
Authors: Jiayi Su, Youhe Feng, Zheng Li, Jinhua Song, Yangfan He, Botao Ren, Botian Xu
Abstract: This paper presents a novel framework for modeling and conditional generation of 3D articulated objects. Troubled by flexibility-quality tradeoffs, existing methods are often limited to using predefined structures or retrieving shapes from static datasets. To address these challenges, we parameterize an articulated object as a tree of tokens and employ a transformer to generate both the object's high-level geometry code and its kinematic relations. Subsequently, each sub-part's geometry is further decoded using a signed-distance-function (SDF) shape prior, facilitating the synthesis of high-quality 3D shapes. Our approach enables the generation of diverse objects with high-quality geometry and varying number of parts. Comprehensive experiments on conditional generation from text descriptions demonstrate the effectiveness and flexibility of our method.
Authors: Arijit Ray, Jiafei Duan, Ellis Brown, Reuben Tan, Dina Bashkirova, Rose Hendrix, Kiana Ehsani, Aniruddha Kembhavi, Bryan A. Plummer, Ranjay Krishna, Kuo-Hao Zeng, Kate Saenko
Abstract: Reasoning about motion and space is a fundamental cognitive capability that is required by multiple real-world applications. While many studies highlight that large multimodal language models (MLMs) struggle to reason about space, they only focus on static spatial relationships, and not dynamic awareness of motion and space, i.e., reasoning about the effect of egocentric and object motions on spatial relationships. Manually annotating such object and camera movements is expensive. Hence, we introduce SAT, a simulated spatial aptitude training dataset comprising both static and dynamic spatial reasoning across 175K question-answer (QA) pairs and 20K scenes. Complementing this, we also construct a small (150 image-QAs) yet challenging dynamic spatial test set using real-world images. Leveraging our SAT datasets and 6 existing static spatial benchmarks, we systematically investigate what improves both static and dynamic spatial awareness. Our results reveal that simulations are surprisingly effective at imparting spatial aptitude to MLMs that translate to real images. We show that perfect annotations in simulation are more effective than existing approaches of pseudo-annotating real images. For instance, SAT training improves a LLaVA-13B model by an average 11% and a LLaVA-Video-7B model by an average 8% on multiple spatial benchmarks, including our real-image dynamic test set and spatial reasoning on long videos -- even outperforming some large proprietary models. While reasoning over static relationships improves with synthetic training data, there is still considerable room for improvement for dynamic reasoning questions.
Authors: Ali Athar, Xueqing Deng, Liang-Chieh Chen
Abstract: Recent advances in multimodal large language models (MLLMs) have expanded research in video understanding, primarily focusing on high-level tasks such as video captioning and question-answering. Meanwhile, a smaller body of work addresses dense, pixel-precise segmentation tasks, which typically involve category-guided or referral-based object segmentation. Although both directions are essential for developing models with human-level video comprehension, they have largely evolved separately, with distinct benchmarks and architectures. This paper aims to unify these efforts by introducing ViCaS, a new dataset containing thousands of challenging videos, each annotated with detailed, human-written captions and temporally consistent, pixel-accurate masks for multiple objects with phrase grounding. Our benchmark evaluates models on both holistic/high-level understanding and language-guided, pixel-precise segmentation. We also present carefully validated evaluation measures and propose an effective model architecture that can tackle our benchmark. Project page: https://ali2500.github.io/vicas-project/
Authors: Yuqing Wang, Shuhuai Ren, Zhijie Lin, Yujin Han, Haoyuan Guo, Zhenheng Yang, Difan Zou, Jiashi Feng, Xihui Liu
Abstract: Autoregressive models have emerged as a powerful approach for visual generation but suffer from slow inference speed due to their sequential token-by-token prediction process. In this paper, we propose a simple yet effective approach for parallelized autoregressive visual generation that improves generation efficiency while preserving the advantages of autoregressive modeling. Our key insight is that parallel generation depends on visual token dependencies-tokens with weak dependencies can be generated in parallel, while strongly dependent adjacent tokens are difficult to generate together, as their independent sampling may lead to inconsistencies. Based on this observation, we develop a parallel generation strategy that generates distant tokens with weak dependencies in parallel while maintaining sequential generation for strongly dependent local tokens. Our approach can be seamlessly integrated into standard autoregressive models without modifying the architecture or tokenizer. Experiments on ImageNet and UCF-101 demonstrate that our method achieves a 3.6x speedup with comparable quality and up to 9.5x speedup with minimal quality degradation across both image and video generation tasks. We hope this work will inspire future research in efficient visual generation and unified autoregressive modeling. Project page: https://yuqingwang1029.github.io/PAR-project.
Authors: Fabrizio Guillaro, Giada Zingarini, Ben Usman, Avneesh Sud, Davide Cozzolino, Luisa Verdoliva
Abstract: Successful forensic detectors can produce excellent results in supervised learning benchmarks but struggle to transfer to real-world applications. We believe this limitation is largely due to inadequate training data quality. While most research focuses on developing new algorithms, less attention is given to training data selection, despite evidence that performance can be strongly impacted by spurious correlations such as content, format, or resolution. A well-designed forensic detector should detect generator specific artifacts rather than reflect data biases. To this end, we propose B-Free, a bias-free training paradigm, where fake images are generated from real ones using the conditioning procedure of stable diffusion models. This ensures semantic alignment between real and fake images, allowing any differences to stem solely from the subtle artifacts introduced by AI generation. Through content-based augmentation, we show significant improvements in both generalization and robustness over state-of-the-art detectors and more calibrated results across 27 different generative models, including recent releases, like FLUX and Stable Diffusion 3.5. Our findings emphasize the importance of a careful dataset design, highlighting the need for further research on this topic. Code and data are publicly available at https://grip-unina.github.io/B-Free/.
Authors: Siyuan Bian, Chenghao Xu, Yuliang Xiu, Artur Grigorev, Zhen Liu, Cewu Lu, Michael J. Black, Yao Feng
Abstract: We introduce ChatGarment, a novel approach that leverages large vision-language models (VLMs) to automate the estimation, generation, and editing of 3D garments from images or text descriptions. Unlike previous methods that struggle in real-world scenarios or lack interactive editing capabilities, ChatGarment can estimate sewing patterns from in-the-wild images or sketches, generate them from text descriptions, and edit garments based on user instructions, all within an interactive dialogue. These sewing patterns can then be draped on a 3D body and animated. This is achieved by finetuning a VLM to directly generate a JSON file that includes both textual descriptions of garment types and styles, as well as continuous numerical attributes. This JSON file is then used to create sewing patterns through a programming parametric model. To support this, we refine the existing programming model, GarmentCode, by expanding its garment type coverage and simplifying its structure for efficient VLM fine-tuning. Additionally, we construct a large-scale dataset of image-to-sewing-pattern and text-to-sewing-pattern pairs through an automated data pipeline. Extensive evaluations demonstrate ChatGarment's ability to accurately reconstruct, generate, and edit garments from multimodal inputs, highlighting its potential to simplify workflows in fashion and gaming applications. Code and data are available at https://chatgarment.github.io/ .
Authors: Chenyang Lei, Meiying Zhang, Weiyuan Peng, Qi Hao, Chengzhong Xu, Chunlin Ji, Guang Zhou
Abstract: Most autonomous driving (AD) datasets incur substantial costs for collection and labeling, inevitably yielding a plethora of low-quality and redundant data instances, thereby compromising performance and efficiency. Many applications in AD systems necessitate high-quality training datasets using both existing datasets and newly collected data. In this paper, we propose a traffic scene joint active learning (TSceneJAL) framework that can efficiently sample the balanced, diverse, and complex traffic scenes from both labeled and unlabeled data. The novelty of this framework is threefold: 1) a scene sampling scheme based on a category entropy, to identify scenes containing multiple object classes, thus mitigating class imbalance for the active learner; 2) a similarity sampling scheme, estimated through the directed graph representation and a marginalize kernel algorithm, to pick sparse and diverse scenes; 3) an uncertainty sampling scheme, predicted by a mixture density network, to select instances with the most unclear or complex regression outcomes for the learner. Finally, the integration of these three schemes in a joint selection strategy yields an optimal and valuable subdataset. Experiments on the KITTI, Lyft, nuScenes and SUScape datasets demonstrate that our approach outperforms existing state-of-the-art methods on 3D object detection tasks with up to 12% improvements.
Authors: Yifei Liu, Zhihang Zhong, Yifan Zhan, Sheng Xu, Xiao Sun
Abstract: While 3D Gaussian Splatting (3DGS) has demonstrated remarkable performance in novel view synthesis and real-time rendering, the high memory consumption due to the use of millions of Gaussians limits its practicality. To mitigate this issue, improvements have been made by pruning unnecessary Gaussians, either through a hand-crafted criterion or by using learned masks. However, these methods deterministically remove Gaussians based on a snapshot of the pruning moment, leading to sub-optimized reconstruction performance from a long-term perspective. To address this issue, we introduce MaskGaussian, which models Gaussians as probabilistic entities rather than permanently removing them, and utilize them according to their probability of existence. To achieve this, we propose a masked-rasterization technique that enables unused yet probabilistically existing Gaussians to receive gradients, allowing for dynamic assessment of their contribution to the evolving scene and adjustment of their probability of existence. Hence, the importance of Gaussians iteratively changes and the pruned Gaussians are selected diversely. Extensive experiments demonstrate the superiority of the proposed method in achieving better rendering quality with fewer Gaussians than previous pruning methods, pruning over 60% of Gaussians on average with only a 0.02 PSNR decline. Our code can be found at: https://github.com/kaikai23/MaskGaussian
Authors: Netanel Y. Tamir, Shir Amir, Ranel Itzhaky, Noam Atia, Shobhita Sundaram, Stephanie Fu, Ron Sokolovsky, Phillip Isola, Tali Dekel, Richard Zhang, Miriam Farber
Abstract: With rapid advancements in virtual reality (VR) headsets, effectively measuring stereoscopic quality of experience (SQoE) has become essential for delivering immersive and comfortable 3D experiences. However, most existing stereo metrics focus on isolated aspects of the viewing experience such as visual discomfort or image quality, and have traditionally faced data limitations. To address these gaps, we present SCOPE (Stereoscopic COntent Preference Evaluation), a new dataset comprised of real and synthetic stereoscopic images featuring a wide range of common perceptual distortions and artifacts. The dataset is labeled with preference annotations collected on a VR headset, with our findings indicating a notable degree of consistency in user preferences across different headsets. Additionally, we present iSQoE, a new model for stereo quality of experience assessment trained on our dataset. We show that iSQoE aligns better with human preferences than existing methods when comparing mono-to-stereo conversion methods.
Authors: Cecilia Curreli, Dominik Muhle, Abhishek Saroha, Zhenzhang Ye, Riccardo Marin, Daniel Cremers
Abstract: Probabilistic human motion prediction aims to forecast multiple possible future movements from past observations. While current approaches report high diversity and realism, they often generate motions with undetected limb stretching and jitter. To address this, we introduce SkeletonDiffusion, a latent diffusion model that embeds an explicit inductive bias on the human body within its architecture and training. Our model is trained with a novel nonisotropic Gaussian diffusion formulation that aligns with the natural kinematic structure of the human skeleton. Results show that our approach outperforms conventional isotropic alternatives, consistently generating realistic predictions while avoiding artifacts such as limb distortion. Additionally, we identify a limitation in commonly used diversity metrics, which may inadvertently favor models that produce inconsistent limb lengths within the same sequence. SkeletonDiffusion sets a new benchmark on real-world datasets, outperforming various baselines across multiple evaluation metrics. Visit our project page at https://ceveloper.github.io/publications/skeletondiffusion/ .
URLs: https://ceveloper.github.io/publications/skeletondiffusion/
Authors: Yaqing Ding, Viktor Kocur, V\'aclav V\'avra, Zuzana Berger Haladov\'a, Jian Yang, Torsten Sattler, Zuzana Kukelova
Abstract: Recent advances in monocular depth estimation methods (MDE) and their improved accuracy open new possibilities for their applications. In this paper, we investigate how monocular depth estimates can be used for relative pose estimation. In particular, we are interested in answering the question whether using MDEs improves results over traditional point-based methods. We propose a novel framework for estimating the relative pose of two cameras from point correspondences with associated monocular depths. Since depth predictions are typically defined up to an unknown scale or even both unknown scale and shift parameters, our solvers jointly estimate the scale or both the scale and shift parameters along with the relative pose. We derive efficient solvers considering different types of depths for three camera configurations: (1) two calibrated cameras, (2) two cameras with an unknown shared focal length, and (3) two cameras with unknown different focal lengths. Our new solvers outperform state-of-the-art depth-aware solvers in terms of speed and accuracy. In extensive real experiments on multiple datasets and with various MDEs, we discuss which depth-aware solvers are preferable in which situation. The code will be made publicly available.
Authors: Marcel Rogge, Didier Stricker
Abstract: Current Gaussian Splatting approaches are effective for reconstructing entire scenes but lack the option to target specific objects, making them computationally expensive and unsuitable for object-specific applications. We propose a novel approach that leverages object masks to enable targeted reconstruction, resulting in object-centric models. Additionally, we introduce an occlusion-aware pruning strategy to minimize the number of Gaussians without compromising quality. Our method reconstructs compact object models, yielding object-centric Gaussian and mesh representations that are up to 96% smaller and up to 71% faster to train compared to the baseline while retaining competitive quality. These representations are immediately usable for downstream applications such as appearance editing and physics simulation without additional processing.
Authors: Hualie Jiang, Zhiqiang Lou, Laiyan Ding, Rui Xu, Minglang Tan, Wenjie Jiang, Rui Huang
Abstract: Stereo matching is a key technique for metric depth estimation in computer vision and robotics. Real-world challenges like occlusion and non-texture hinder accurate disparity estimation from binocular matching cues. Recently, monocular relative depth estimation has shown remarkable generalization using vision foundation models. Thus, to facilitate robust stereo matching with monocular depth cues, we incorporate a robust monocular relative depth model into the recurrent stereo-matching framework, building a new framework for depth foundation model-based stereo-matching, DEFOM-Stereo. In the feature extraction stage, we construct the combined context and matching feature encoder by integrating features from conventional CNNs and DEFOM. In the update stage, we use the depth predicted by DEFOM to initialize the recurrent disparity and introduce a scale update module to refine the disparity at the correct scale. DEFOM-Stereo is verified to have much stronger zero-shot generalization compared with SOTA methods. Moreover, DEFOM-Stereo achieves top performance on the KITTI 2012, KITTI 2015, Middlebury, and ETH3D benchmarks, ranking $1^{st}$ on many metrics. In the joint evaluation under the robust vision challenge, our model simultaneously outperforms previous models on the individual benchmarks, further demonstrating its outstanding capabilities.
Authors: Wenbo Xiao, Zhihao Xu, Guiping Liang, Yangjun Deng, Yi Xiao
Abstract: Semi-supervised medical image segmentation aims to leverage minimal expert annotations, yet remains confronted by challenges in maintaining high-quality consistency learning. Excessive perturbations can degrade alignment and hinder precise decision boundaries, especially in regions with uncertain predictions. In this paper, we introduce Confidence-Aware Adaptive Displacement (CAD), a framework that selectively identifies and replaces the largest low-confidence regions with high-confidence patches. By dynamically adjusting both the maximum allowable replacement size and the confidence threshold throughout training, CAD progressively refines the segmentation quality without overwhelming the learning process. Experimental results on public medical datasets demonstrate that CAD effectively enhances segmentation quality, establishing new state-of-the-art accuracy in this field. The source code will be released after the paper is published.
Authors: Xuyin Qi, Zeyu Zhang, Huazhan Zheng, Mingxi Chen, Numan Kutaiba, Ruth Lim, Cherie Chiang, Zi En Tham, Xuan Ren, Wenxin Zhang, Lei Zhang, Hao Zhang, Wenbing Lv, Guangzhen Yao, Renda Han, Kangsheng Wang, Mingyuan Li, Hongtao Mao, Yu Li, Zhibin Liao, Yang Zhao, Minh-Son To
Abstract: Bone density prediction via CT scans to estimate T-scores is crucial, providing a more precise assessment of bone health compared to traditional methods like X-ray bone density tests, which lack spatial resolution and the ability to detect localized changes. However, CT-based prediction faces two major challenges: the high computational complexity of transformer-based architectures, which limits their deployment in portable and clinical settings, and the imbalanced, long-tailed distribution of real-world hospital data that skews predictions. To address these issues, we introduce MedConv, a convolutional model for bone density prediction that outperforms transformer models with lower computational demands. We also adapt Bal-CE loss and post-hoc logit adjustment to improve class balance. Extensive experiments on our AustinSpine dataset shows that our approach achieves up to 21% improvement in accuracy and 20% in ROC AUC over previous state-of-the-art methods.
Authors: Baoyao Yang, Junxiang Chen, Wanyun Li, Wenbin Yao, Yang Zhou
Abstract: Video-text retrieval has been stuck in the information mismatch caused by personalized and inadequate textual descriptions of videos. The substantial information gap between the two modalities hinders an effective cross-modal representation alignment, resulting in ambiguous retrieval results. Although text rewriting methods have been proposed to broaden text expressions, the modality gap remains significant, as the text representation space is hardly expanded with insufficient semantic enrichment.Instead, this paper turns to enhancing visual presentation, bridging video expression closer to textual representation via caption generation and thereby facilitating video-text matching.While multimodal large language models (mLLM) have shown a powerful capability to convert video content into text, carefully crafted prompts are essential to ensure the reasonableness and completeness of the generated captions. Therefore, this paper proposes an automatic caption enhancement method that improves expression quality and mitigates empiricism in augmented captions through self-learning.Additionally, an expertized caption selection mechanism is designed and introduced to customize augmented captions for each video, further exploring the utilization potential of caption augmentation.Our method is entirely data-driven, which not only dispenses with heavy data collection and computation workload but also improves self-adaptability by circumventing lexicon dependence and introducing personalized matching. The superiority of our method is validated by state-of-the-art results on various benchmarks, specifically achieving Top-1 recall accuracy of 68.5% on MSR-VTT, 68.1% on MSVD, and 62.0% on DiDeMo. Our code is publicly available at https://github.com/CaryXiang/ECA4VTR.
Authors: Joseph Paul Cohen, Louis Blankemeier, Akshay Chaudhari
Abstract: Counterfactual explanations enhance the interpretability of deep learning models in medical imaging, yet adapting them to 3D CT scans poses challenges due to volumetric complexity and resource demands. We extend the Latent Shift counterfactual generation method from 2D applications to explain 3D computed tomography (CT) scans classifiers. We address the challenges associated with 3D classifiers, such as limited training samples and high memory demands, by implementing a slice-based autoencoder and gradient blocking except for specific chunks of slices. This method leverages a 2D encoder trained on CT slices, which are subsequently combined to maintain 3D context. We demonstrate this technique on two models for clinical phenotype prediction and lung segmentation. Our approach is both memory-efficient and effective for generating interpretable counterfactuals in high-resolution 3D medical imaging.
Authors: Nikolaos Dionelis, Jente Bosmans, Nicolas Long\'ep\'e
Abstract: Performing accurate confidence quantification and assessment in pixel-wise regression tasks, which are downstream applications of AI Foundation Models for Earth Observation (EO), is important for deep neural networks to predict their failures, improve their performance and enhance their capabilities in real-world applications, for their practical deployment. For pixel-wise regression tasks, specifically utilizing remote sensing data from satellite imagery in EO Foundation Models, confidence quantification is a critical challenge. The focus of this research work is on developing a Foundation Model using EO satellite data that computes and assigns a confidence metric alongside regression outputs to improve the reliability and interpretability of predictions generated by deep neural networks. To this end, we develop, train and evaluate the proposed Confidence-Aware Regression Estimation (CARE) Foundation Model. Our model CARE computes and assigns confidence to regression results as downstream tasks of a Foundation Model for EO data, and performs a confidence-aware self-corrective learning method for the low-confidence regions. We evaluate the model CARE, and experimental results on multi-spectral data from the Copernicus Sentinel-2 satellite constellation to estimate the building density (i.e. monitoring urban growth), show that the proposed method can be successfully applied to important regression problems in EO and remote sensing. We also show that our model CARE outperforms other baseline methods.
Authors: Aysegul Ucar, Soumyadeep Ro, Sanapala Satwika, Pamarthi Yasoda Gayathri, Mohmmad Ghaith Balsha
Abstract: Vision-Language Models (VLMs) have emerged as powerful tools in artificial intelli-gence, capable of integrating textual and visual data for a unified understanding of complex scenes. While models such as Florence2, built on transformer architectures, have shown promise across general tasks, their performance in object detection within unstructured or cluttered environments remains underexplored. In this study, we fi-ne-tuned the Florence2 model for object detection tasks in non-constructed, complex environments. A comprehensive experimental framework was established involving multiple hardware configurations (NVIDIA T4, L4, and A100 GPUs), optimizers (AdamW, SGD), and varied hyperparameters including learning rates and LoRA (Low-Rank Adaptation) setups. Model training and evaluation were conducted on challenging datasets representative of real-world, disordered settings. The optimized Florence2 models exhibited significant improvements in object detection accuracy, with Mean Average Precision (mAP) metrics approaching or matching those of estab-lished models such as YOLOv8, YOLOv9, and YOLOv10. The integration of LoRA and careful fine-tuning of transformer layers contributed notably to these gains. Our find-ings highlight the adaptability of transformer-based VLMs like Florence2 for do-main-specific tasks, particularly in visually complex environments. The study under-scores the potential of fine-tuned VLMs to rival traditional convolution-based detec-tors, offering a flexible and scalable approach for advanced vision applications in re-al-world, unstructured settings.
Authors: Yan Wang, Shijie Zhao, Kai Chen, Kexin Zhang, Junlin Li, Li Zhang
Abstract: Recent research applying text-to-image (T2I) diffusion models to real-world super-resolution (SR) has achieved remarkable success. However, fundamental misalignments between T2I and SR targets result in a dilemma between inference speed and detail fidelity. Specifically, T2I tasks prioritize multi-step inversion to synthesize coherent outputs aligned with textual prompts and shrink the latent space to reduce generating complexity. Contrariwise, SR tasks preserve most information from low-resolution input while solely restoring high-frequency details, thus necessitating sufficient latent space and fewer inference steps. To bridge the gap, we present a one-step diffusion model for generative detail restoration, GenDR, distilled from a tailored diffusion model with larger latent space. In detail, we train a new SD2.1-VAE16 (0.9B) via representation alignment to expand latent space without enlarging the model size. Regarding step-distillation, we propose consistent score identity distillation (CiD) that incorporates SR task-specific loss into score distillation to leverage more SR priors and align the training target. Furthermore, we extend CiD with adversarial learning and representation alignment (CiDA) to enhance perceptual quality and accelerate training. We also polish the pipeline to achieve a more efficient inference. Experimental results demonstrate that GenDR achieves state-of-the-art performance in both quantitative metrics and visual fidelity.
Authors: Jianhui Wang, Zhifei Yang, Yangfan He, Huixiong Zhang, Yuxuan Chen, Jingwei Huang
Abstract: Accurate material retrieval is critical for creating realistic 3D assets. Existing methods rely on datasets that capture shape-invariant and lighting-varied representations of materials, which are scarce and face challenges due to limited diversity and inadequate real-world generalization. Most current approaches adopt traditional image search techniques. They fall short in capturing the unique properties of material spaces, leading to suboptimal performance in retrieval tasks. Addressing these challenges, we introduce MaRI, a framework designed to bridge the feature space gap between synthetic and real-world materials. MaRI constructs a shared embedding space that harmonizes visual and material attributes through a contrastive learning strategy by jointly training an image and a material encoder, bringing similar materials and images closer while separating dissimilar pairs within the feature space. To support this, we construct a comprehensive dataset comprising high-quality synthetic materials rendered with controlled shape variations and diverse lighting conditions, along with real-world materials processed and standardized using material transfer techniques. Extensive experiments demonstrate the superior performance, accuracy, and generalization capabilities of MaRI across diverse and complex material retrieval tasks, outperforming existing methods.
Authors: Kyle Sargent, Kyle Hsu, Justin Johnson, Li Fei-Fei, Jiajun Wu
Abstract: Since the advent of popular visual generation frameworks like VQGAN and latent diffusion models, state-of-the-art image generation systems have generally been two-stage systems that first tokenize or compress visual data into a lower-dimensional latent space before learning a generative model. Tokenizer training typically follows a standard recipe in which images are compressed and reconstructed subject to a combination of MSE, perceptual, and adversarial losses. Diffusion autoencoders have been proposed in prior work as a way to learn end-to-end perceptually-oriented image compression, but have not yet shown state-of-the-art performance on the competitive task of ImageNet-1K reconstruction. We propose FlowMo, a transformer-based diffusion autoencoder that achieves a new state-of-the-art for image tokenization at multiple compression rates without using convolutions, adversarial losses, spatially-aligned two-dimensional latent codes, or distilling from other tokenizers. Our key insight is that FlowMo training should be broken into a mode-matching pre-training stage and a mode-seeking post-training stage. In addition, we conduct extensive analyses and explore the training of generative models atop the FlowMo tokenizer. Our code and models will be available at http://kylesargent.github.io/flowmo .
Authors: Xiang Li, Heqian Qiu, Lanxiao Wang, Hanwen Zhang, Chenghao Qi, Linfeng Han, Huiyu Xiong, Hongliang Li
Abstract: With the rapid development of artificial intelligence technologies and wearable devices, egocentric vision understanding has emerged as a new and challenging research direction, gradually attracting widespread attention from both academia and industry. Egocentric vision captures visual and multimodal data through cameras or sensors worn on the human body, offering a unique perspective that simulates human visual experiences. This paper provides a comprehensive survey of the research on egocentric vision understanding, systematically analyzing the components of egocentric scenes and categorizing the tasks into four main areas: subject understanding, object understanding, environment understanding, and hybrid understanding. We explore in detail the sub-tasks within each category. We also summarize the main challenges and trends currently existing in the field. Furthermore, this paper presents an overview of high-quality egocentric vision datasets, offering valuable resources for future research. By summarizing the latest advancements, we anticipate the broad applications of egocentric vision technologies in fields such as augmented reality, virtual reality, and embodied intelligence, and propose future research directions based on the latest developments in the field.
Authors: Haichao Zhang, Yun Fu
Abstract: Token-based video representation has emerged as a promising approach for enabling LLMs to interpret video content. However, existing token reduction, such as token pruning and token merging, often disrupt essential spatial-temporal positional embeddings, failing to adequately balance computational efficiency with fewer tokens. Consequently, these methods result in lengthy token sequences, limiting their applicability in scenarios requiring extreme token compression, such as video large language models. In this paper, we introduce the novel task of extreme short token reduction, aiming to represent extensive video sequences with a minimal number of tokens. To address this challenge, we propose Token Dynamics, a new video representation framework that dynamically reduces token count while preserving spatial-temporal coherence. Specifically, we disentangle video representations by separating visual embeddings from grid-level motion information, structuring them into: 1. a concise token hash table, created by clustering tokens that describe object-level content; 2. a token indices key map, capturing detailed spatial-temporal motion patterns across grids; 3. a token hash function, which vector-quantizes the token hash table to reconstruct the token sequence from the key map. Furthermore, we introduce a cross-dynamics attention mechanism that integrates motion features into the token base without increasing token length, thereby maintaining compactness and spatial-temporal integrity. The experiments demonstrate a reduction of token count to merely 0.07% of the original tokens, with only a minor performance drop of 1.13%. Additionally, we propose two novel subtasks within extreme token reduction (fixed-length and adaptive-length compression). Our method offers significantly lower theoretical complexity, fewer tokens, and enhanced throughput, thus providing an efficient solution for video LLMs.
Authors: Weichen Fan, Amber Yijia Zheng, Raymond A. Yeh, Ziwei Liu
Abstract: Classifier-Free Guidance (CFG) is a widely adopted technique in diffusion/flow models to improve image fidelity and controllability. In this work, we first analytically study the effect of CFG on flow matching models trained on Gaussian mixtures where the ground-truth flow can be derived. We observe that in the early stages of training, when the flow estimation is inaccurate, CFG directs samples toward incorrect trajectories. Building on this observation, we propose CFG-Zero*, an improved CFG with two contributions: (a) optimized scale, where a scalar is optimized to correct for the inaccuracies in the estimated velocity, hence the * in the name; and (b) zero-init, which involves zeroing out the first few steps of the ODE solver. Experiments on both text-to-image (Lumina-Next, Stable Diffusion 3, and Flux) and text-to-video (Wan-2.1) generation demonstrate that CFG-Zero* consistently outperforms CFG, highlighting its effectiveness in guiding Flow Matching models. (Code is available at github.com/WeichenFan/CFG-Zero-star)
Authors: Liang Pan, Zeshi Yang, Zhiyang Dou, Wenjia Wang, Buzhen Huang, Bo Dai, Taku Komura, Jingbo Wang
Abstract: Synthesizing diverse and physically plausible Human-Scene Interactions (HSI) is pivotal for both computer animation and embodied AI. Despite encouraging progress, current methods mainly focus on developing separate controllers, each specialized for a specific interaction task. This significantly hinders the ability to tackle a wide variety of challenging HSI tasks that require the integration of multiple skills, e.g., sitting down while carrying an object. To address this issue, we present TokenHSI, a single, unified transformer-based policy capable of multi-skill unification and flexible adaptation. The key insight is to model the humanoid proprioception as a separate shared token and combine it with distinct task tokens via a masking mechanism. Such a unified policy enables effective knowledge sharing across skills, thereby facilitating the multi-task training. Moreover, our policy architecture supports variable length inputs, enabling flexible adaptation of learned skills to new scenarios. By training additional task tokenizers, we can not only modify the geometries of interaction targets but also coordinate multiple skills to address complex tasks. The experiments demonstrate that our approach can significantly improve versatility, adaptability, and extensibility in various HSI tasks. Website: https://liangpan99.github.io/TokenHSI/
Authors: Yuhan Wang, Suzhi Bi, Ying-Jun Angela Zhang, Xiaojun Yuan
Abstract: The distortion-perception (DP) tradeoff reveals a fundamental conflict between distortion metrics (e.g., MSE and PSNR) and perceptual quality. Recent research has increasingly concentrated on evaluating denoising algorithms within the DP framework. However, existing algorithms either prioritize perceptual quality by sacrificing acceptable distortion, or focus on minimizing MSE for faithful restoration. When the goal shifts or noisy measurements vary, adapting to different points on the DP plane needs retraining or even re-designing the model. Inspired by recent advances in solving inverse problems using score-based generative models, we explore the potential of flexibly and optimally traversing DP tradeoffs using a single pre-trained score-based model. Specifically, we introduce a variance-scaled reverse diffusion process and theoretically characterize the marginal distribution. We then prove that the proposed sample process is an optimal solution to the DP tradeoff for conditional Gaussian distribution. Experimental results on two-dimensional and image datasets illustrate that a single score network can effectively and flexibly traverse the DP tradeoff for general denoising problems.
Authors: Silin Gao, Sheryl Mathew, Li Mi, Sepideh Mamooler, Mengjie Zhao, Hiromi Wakaki, Yuki Mitsufuji, Syrielle Montariol, Antoine Bosselut
Abstract: Visual narrative generation transforms textual narratives into sequences of images illustrating the content of the text. However, generating visual narratives that are faithful to the input text and self-consistent across generated images remains an open challenge, due to the lack of knowledge constraints used for planning the stories. In this work, we propose a new benchmark, VinaBench, to address this challenge. Our benchmark annotates the underlying commonsense and discourse constraints in visual narrative samples, offering systematic scaffolds for learning the implicit strategies of visual storytelling. Based on the incorporated narrative constraints, we further propose novel metrics to closely evaluate the consistency of generated narrative images and the alignment of generations with the input textual narrative. Our results across three generative vision models demonstrate that learning with VinaBench's knowledge constraints effectively improves the faithfulness and cohesion of generated visual narratives.
Authors: Roxana Bujack, Emily Shinkle, Alice Allen, Tomas Suk, Nicholas Lubbers
Abstract: Moment invariants are a powerful tool for the generation of rotation-invariant descriptors needed for many applications in pattern detection, classification, and machine learning. A set of invariants is optimal if it is complete, independent, and robust against degeneracy in the input. In this paper, we show that the current state of the art for the generation of these bases of moment invariants, despite being robust against moment tensors being identically zero, is vulnerable to a degeneracy that is common in real-world applications, namely spherical functions. We show how to overcome this vulnerability by combining two popular moment invariant approaches: one based on spherical harmonics and one based on Cartesian tensor algebra.
Authors: Yujie Chen, Haotong Qin, Zhang Zhang, Michelo Magno, Luca Benini, Yawei Li
Abstract: State-Space Models (SSMs) have attracted considerable attention in Image Restoration (IR) due to their ability to scale linearly sequence length while effectively capturing long-distance dependencies. However, deploying SSMs to edge devices is challenging due to the constraints in memory, computing capacity, and power consumption, underscoring the need for efficient compression strategies. While low-bit quantization is an efficient model compression strategy for reducing size and accelerating IR tasks, SSM suffers substantial performance drops at ultra-low bit-widths (2-4 bits), primarily due to outliers that exacerbate quantization error. To address this challenge, we propose Q-MambaIR, an accurate, efficient, and flexible Quantized Mamba for IR tasks. Specifically, we introduce a Statistical Dynamic-balancing Learnable Scalar (DLS) to dynamically adjust the quantization mapping range, thereby mitigating the peak truncation loss caused by extreme values. Furthermore, we design a Range-floating Flexible Allocator (RFA) with an adaptive threshold to flexibly round values. This approach preserves high-frequency details and maintains the SSM's feature extraction capability. Notably, RFA also enables pre-deployment weight quantization, striking a balance between computational efficiency and model accuracy. Extensive experiments on IR tasks demonstrate that Q-MambaIR consistently outperforms existing quantized SSMs, achieving much higher state-of-the-art (SOTA) accuracy results with only a negligible increase in training computation and storage saving.
Authors: Jiahui Zhang, Yurui Chen, Yanpeng Zhou, Yueming Xu, Ze Huang, Jilin Mei, Junhui Chen, Yu-Jie Yuan, Xinyue Cai, Guowei Huang, Xingyue Quan, Hang Xu, Li Zhang
Abstract: Recent advances in LVLMs have improved vision-language understanding, but they still struggle with spatial perception, limiting their ability to reason about complex 3D scenes. Unlike previous approaches that incorporate 3D representations into models to improve spatial understanding, we aim to unlock the potential of VLMs by leveraging spatially relevant image data. To this end, we introduce a novel 2D spatial data generation and annotation pipeline built upon scene data with 3D ground-truth. This pipeline enables the creation of a diverse set of spatial tasks, ranging from basic perception tasks to more complex reasoning tasks. Leveraging this pipeline, we construct SPAR-7M, a large-scale dataset generated from thousands of scenes across multiple public datasets. In addition, we introduce SPAR-Bench, a benchmark designed to offer a more comprehensive evaluation of spatial capabilities compared to existing spatial benchmarks, supporting both single-view and multi-view inputs. Training on both SPAR-7M and large-scale 2D datasets enables our models to achieve state-of-the-art performance on 2D spatial benchmarks. Further fine-tuning on 3D task-specific datasets yields competitive results, underscoring the effectiveness of our dataset in enhancing spatial reasoning.
Authors: Pengyu Chen, Sicheng Wang, Cuizhen Wang, Senrong Wang, Beiao Huang, Lu Huang, Zhe Zang
Abstract: Precise detection of rooftops from historical aerial imagery is essential for analyzing long-term urban development and human settlement patterns. Nonetheless, black-and-white analog photographs present considerable challenges for modern object detection frameworks due to their limited spatial resolution, absence of color information, and archival degradation. To address these challenges, this research introduces a two-stage image enhancement pipeline based on Generative Adversarial Networks (GANs): image colorization utilizing DeOldify, followed by super-resolution enhancement with Real-ESRGAN. The enhanced images were subsequently employed to train and evaluate rooftop detection models, including Faster R-CNN, DETReg, and YOLOv11n. The results demonstrate that the combination of colorization with super-resolution significantly enhances detection performance, with YOLOv11n achieving a mean Average Precision (mAP) exceeding 85\%. This signifies an enhancement of approximately 40\% over the original black-and-white images and 20\% over images enhanced solely through colorization. The proposed method effectively bridges the gap between archival imagery and contemporary deep learning techniques, facilitating more reliable extraction of building footprints from historical aerial photographs. Code and resources for reproducing our results are publicly available at \href{https://github.com/Pengyu-gis/Historical-Aerial-Photos}{github.com/Pengyu-gis/Historical-Aerial-Photos}.
URLs: https://github.com/Pengyu-gis/Historical-Aerial-Photos
Authors: Anwesa Choudhuri, Zhongpai Gao, Meng Zheng, Benjamin Planche, Terrence Chen, Ziyan Wu
Abstract: Early detection, accurate segmentation, classification and tracking of polyps during colonoscopy are critical for preventing colorectal cancer. Many existing deep-learning-based methods for analyzing colonoscopic videos either require task-specific fine-tuning, lack tracking capabilities, or rely on domain-specific pre-training. In this paper, we introduce PolypSegTrack, a novel foundation model that jointly addresses polyp detection, segmentation, classification and unsupervised tracking in colonoscopic videos. Our approach leverages a novel conditional mask loss, enabling flexible training across datasets with either pixel-level segmentation masks or bounding box annotations, allowing us to bypass task-specific fine-tuning. Our unsupervised tracking module reliably associates polyp instances across frames using object queries, without relying on any heuristics. We leverage a robust vision foundation model backbone that is pre-trained unsupervisedly on natural images, thereby removing the need for domain-specific pre-training. Extensive experiments on multiple polyp benchmarks demonstrate that our method significantly outperforms existing state-of-the-art approaches in detection, segmentation, classification, and tracking.
Authors: Valentin Boussot, C\'edric H\'emon, Jean-Claude Nunes, Jason Downling, Simon Rouz\'e, Caroline Lafond, Ana\"is Barateau, Jean-Louis Dillenseger
Abstract: Image registration is fundamental in medical imaging, enabling precise alignment of anatomical structures for diagnosis, treatment planning, image-guided interventions, and longitudinal monitoring. This work introduces IMPACT (Image Metric with Pretrained model-Agnostic Comparison for Transmodality registration), a novel similarity metric designed for robust multimodal image registration. Rather than relying on raw intensities, handcrafted descriptors, or task-specific training, IMPACT defines a semantic similarity measure based on the comparison of deep features extracted from large-scale pretrained segmentation models. By leveraging representations from models such as TotalSegmentator, Segment Anything (SAM), and other foundation networks, IMPACT provides a task-agnostic, training-free solution that generalizes across imaging modalities. These features, originally trained for segmentation, offer strong spatial correspondence and semantic alignment capabilities, making them naturally suited for registration. The method integrates seamlessly into both algorithmic (Elastix) and learning-based (VoxelMorph) frameworks, leveraging the strengths of each. IMPACT was evaluated on five challenging 3D registration tasks involving thoracic CT/CBCT and pelvic MR/CT datasets. Quantitative metrics, including Target Registration Error and Dice Similarity Coefficient, demonstrated consistent improvements in anatomical alignment over baseline methods. Qualitative analyses further highlighted the robustness of the proposed metric in the presence of noise, artifacts, and modality variations. With its versatility, efficiency, and strong performance across diverse tasks, IMPACT offers a powerful solution for advancing multimodal image registration in both clinical and research settings.
Authors: Hao Qin, Luyuan Chen, Ming Kong, Mengxu Lu, Qiang Zhu
Abstract: We introduce DD3G, a formulation that Distills a multi-view Diffusion model (MV-DM) into a 3D Generator using gaussian splatting. DD3G compresses and integrates extensive visual and spatial geometric knowledge from the MV-DM by simulating its ordinary differential equation (ODE) trajectory, ensuring the distilled generator generalizes better than those trained solely on 3D data. Unlike previous amortized optimization approaches, we align the MV-DM and 3D generator representation spaces to transfer the teacher's probabilistic flow to the student, thus avoiding inconsistencies in optimization objectives caused by probabilistic sampling. The introduction of probabilistic flow and the coupling of various attributes in 3D Gaussians introduce challenges in the generation process. To tackle this, we propose PEPD, a generator consisting of Pattern Extraction and Progressive Decoding phases, which enables efficient fusion of probabilistic flow and converts a single image into 3D Gaussians within 0.06 seconds. Furthermore, to reduce knowledge loss and overcome sparse-view supervision, we design a joint optimization objective that ensures the quality of generated samples through explicit supervision and implicit verification. Leveraging existing 2D generation models, we compile 120k high-quality RGBA images for distillation. Experiments on synthetic and public datasets demonstrate the effectiveness of our method. Our project is available at: https://qinbaigao.github.io/DD3G_project/
Authors: Andrei Dumitriu, Florin Tatui, Florin Miron, Aakash Ralhan, Radu Tudor Ionescu, Radu Timofte
Abstract: Rip currents are strong, localized and narrow currents of water that flow outwards into the sea, causing numerous beach-related injuries and fatalities worldwide. Accurate identification of rip currents remains challenging due to their amorphous nature and the lack of annotated data, which often requires expert knowledge. To address these issues, we present RipVIS, a large-scale video instance segmentation benchmark explicitly designed for rip current segmentation. RipVIS is an order of magnitude larger than previous datasets, featuring $184$ videos ($212,328$ frames), of which $150$ videos ($163,528$ frames) are with rip currents, collected from various sources, including drones, mobile phones, and fixed beach cameras. Our dataset encompasses diverse visual contexts, such as wave-breaking patterns, sediment flows, and water color variations, across multiple global locations, including USA, Mexico, Costa Rica, Portugal, Italy, Greece, Romania, Sri Lanka, Australia and New Zealand. Most videos are annotated at $5$ FPS to ensure accuracy in dynamic scenarios, supplemented by an additional $34$ videos ($48,800$ frames) without rip currents. We conduct comprehensive experiments with Mask R-CNN, Cascade Mask R-CNN, SparseInst and YOLO11, fine-tuning these models for the task of rip current segmentation. Results are reported in terms of multiple metrics, with a particular focus on the $F_2$ score to prioritize recall and reduce false negatives. To enhance segmentation performance, we introduce a novel post-processing step based on Temporal Confidence Aggregation (TCA). RipVIS aims to set a new standard for rip current segmentation, contributing towards safer beach environments. We offer a benchmark website to share data, models, and results with the research community, encouraging ongoing collaboration and future contributions, at https://ripvis.ai.
URLs: https://ripvis.ai.
Authors: Shiyong Liu, Zhihao Li, Xiao Tang, Jianzhuang Liu
Abstract: Most model-based 3D hand pose and shape estimation methods directly regress the parametric model parameters from an image to obtain 3D joints under weak supervision. However, these methods involve solving a complex optimization problem with many local minima, making training difficult. To address this challenge, we propose learning direction-aware hybrid features (DaHyF) that fuse implicit image features and explicit 2D joint coordinate features. This fusion is enhanced by the pixel direction information in the camera coordinate system to estimate pose, shape, and camera viewpoint. Our method directly predicts 3D hand poses with DaHyF representation and reduces jittering during motion capture using prediction confidence based on contrastive learning. We evaluate our method on the FreiHAND dataset and show that it outperforms existing state-of-the-art methods by more than 33% in accuracy. DaHyF also achieves the top ranking on both the HO3Dv2 and HO3Dv3 leaderboards for the metric of Mean Joint Error (after scale and translation alignment). Compared to the second-best results, the largest improvement observed is 10%. We also demonstrate its effectiveness in real-time motion capture scenarios with hand position variability, occlusion, and motion blur.
Authors: Zixuan Wang, Duo Peng, Feng Chen, Yuwei Yang, Yinjie Lei
Abstract: Conditional image synthesis is a crucial task with broad applications, such as artistic creation and virtual reality. However, current generative methods are often task-oriented with a narrow scope, handling a restricted condition with constrained applicability. In this paper, we propose a novel approach that treats conditional image synthesis as the modular combination of diverse fundamental condition units. Specifically, we divide conditions into three primary units: text, layout, and drag. To enable effective control over these conditions, we design a dedicated alignment module for each. For the text condition, we introduce a Dense Concept Alignment (DCA) module, which achieves dense visual-text alignment by drawing on diverse textual concepts. For the layout condition, we propose a Dense Geometry Alignment (DGA) module to enforce comprehensive geometric constraints that preserve the spatial configuration. For the drag condition, we introduce a Dense Motion Alignment (DMA) module to apply multi-level motion regularization, ensuring that each pixel follows its desired trajectory without visual artifacts. By flexibly inserting and combining these alignment modules, our framework enhances the model's adaptability to diverse conditional generation tasks and greatly expands its application range. Extensive experiments demonstrate the superior performance of our framework across a variety of conditions, including textual description, segmentation mask (bounding box), drag manipulation, and their combinations. Code is available at https://github.com/ZixuanWang0525/DADG.
Authors: Adriano Fragomeni, Dima Damen, Michael Wray
Abstract: Video retrieval requires aligning visual content with corresponding natural language descriptions. In this paper, we introduce Modality Auxiliary Concepts for Video Retrieval (MAC-VR), a novel approach that leverages modality-specific tags -- automatically extracted from foundation models -- to enhance video retrieval. We propose to align modalities in a latent space, along with learning and aligning auxiliary latent concepts, derived from the features of a video and its corresponding caption. We introduce these auxiliary concepts to improve the alignment of visual and textual latent concepts, and so are able to distinguish concepts from one other. We conduct extensive experiments on five diverse datasets: MSR-VTT, DiDeMo, TGIF, Charades and YouCook2. The experimental results consistently demonstrate that modality-specific tags improve cross-modal alignment, outperforming current state-of-the-art methods across three datasets and performing comparably or better across the other two.
Authors: Haosheng Li, Junjie Chen, Yuecong Xu, Kemi Ding
Abstract: Unsupervised domain adaptation (UDA) frameworks have shown good generalization capabilities for 3D point cloud semantic segmentation models on clean data. However, existing works overlook adversarial robustness when the source domain itself is compromised. To comprehensively explore the robustness of the UDA frameworks, we first design a stealthy adversarial point cloud generation attack that can significantly contaminate datasets with only minor perturbations to the point cloud surface. Based on that, we propose a novel dataset, AdvSynLiDAR, comprising synthesized contaminated LiDAR point clouds. With the generated corrupted data, we further develop the Adversarial Adaptation Framework (AAF) as the countermeasure. Specifically, by extending the key point sensitive (KPS) loss towards the Robust Long-Tail loss (RLT loss) and utilizing a decoder branch, our approach enables the model to focus on long-tail classes during the pre-training phase and leverages high-confidence decoded point cloud information to restore point cloud structures during the adaptation phase. We evaluated our AAF method on the AdvSynLiDAR dataset, where the results demonstrate that our AAF method can mitigate performance degradation under source adversarial perturbations for UDA in the 3D point cloud segmentation application.
Authors: Kaan Karaman, Yuchang Jiang, Damien Robert, Vivien Sainte Fare Garnot, Maria Jo\~ao Santos, Jan Dirk Wegner
Abstract: Accurate Above-Ground Biomass (AGB) mapping at both large scale and high spatio-temporal resolution is essential for applications ranging from climate modeling to biodiversity assessment, and sustainable supply chain monitoring. At present, fine-grained AGB mapping relies on costly airborne laser scanning acquisition campaigns usually limited to regional scales. Initiatives such as the ESA CCI map attempt to generate global biomass products from diverse spaceborne sensors but at a coarser resolution. To enable global, high-resolution (HR) mapping, several works propose to regress AGB from HR satellite observations such as ESA Sentinel-1/2 images. We propose a novel way to address HR AGB estimation, by leveraging both HR satellite observations and existing low-resolution (LR) biomass products. We cast this problem as Guided Super-Resolution (GSR), aiming at upsampling LR biomass maps (sources) from $100$ to $10$ m resolution, using auxiliary HR co-registered satellite images (guides). We compare super-resolving AGB maps with and without guidance, against direct regression from satellite images, on the public BioMassters dataset. We observe that Multi-Scale Guidance (MSG) outperforms direct regression both for regression ($-780$ t/ha RMSE) and perception ($+2.0$ dB PSNR) metrics, and better captures high-biomass values, without significant computational overhead. Interestingly, unlike the RGB+Depth setting they were originally designed for, our best-performing AGB GSR approaches are those that most preserve the guide image texture. Our results make a strong case for adopting the GSR framework for accurate HR biomass mapping at scale. Our code and model weights are made publicly available (https://github.com/kaankaramanofficial/GSR4B).
Authors: Yuxuan Luo, Zhengkun Rong, Lizhen Wang, Longhao Zhang, Tianshu Hu, Yongming Zhu
Abstract: While recent image-based human animation methods achieve realistic body and facial motion synthesis, critical gaps remain in fine-grained holistic controllability, multi-scale adaptability, and long-term temporal coherence, which leads to their lower expressiveness and robustness. We propose a diffusion transformer (DiT) based framework, DreamActor-M1, with hybrid guidance to overcome these limitations. For motion guidance, our hybrid control signals that integrate implicit facial representations, 3D head spheres, and 3D body skeletons achieve robust control of facial expressions and body movements, while producing expressive and identity-preserving animations. For scale adaptation, to handle various body poses and image scales ranging from portraits to full-body views, we employ a progressive training strategy using data with varying resolutions and scales. For appearance guidance, we integrate motion patterns from sequential frames with complementary visual references, ensuring long-term temporal coherence for unseen regions during complex movements. Experiments demonstrate that our method outperforms the state-of-the-art works, delivering expressive results for portraits, upper-body, and full-body generation with robust long-term consistency. Project Page: https://grisoon.github.io/DreamActor-M1/.
Authors: Runhui Huang, Chunwei Wang, Junwei Yang, Guansong Lu, Yunlong Yuan, Jianhua Han, Lu Hou, Wei Zhang, Lanqing Hong, Hengshuang Zhao, Hang Xu
Abstract: We present ILLUME+ that leverages dual visual tokenization and a diffusion decoder to improve both deep semantic understanding and high-fidelity image generation. Existing unified models have struggled to simultaneously handle the three fundamental capabilities in a unified model: understanding, generation, and editing. Models like Chameleon and EMU3 utilize VQGAN for image discretization, due to the lack of deep semantic interaction, they lag behind specialist models like LLaVA in visual understanding tasks. To mitigate this, LaViT and ILLUME employ semantic encoders for tokenization, but they struggle with image editing due to poor texture preservation. Meanwhile, Janus series decouples the input and output image representation, limiting their abilities to seamlessly handle interleaved image-text understanding and generation. In contrast, ILLUME+ introduces a unified dual visual tokenizer, DualViTok, which preserves both fine-grained textures and text-aligned semantics while enabling a coarse-to-fine image representation strategy for multimodal understanding and generation. Additionally, we employ a diffusion model as the image detokenizer for enhanced generation quality and efficient super-resolution. ILLUME+ follows a continuous-input, discrete-output scheme within the unified MLLM and adopts a progressive training procedure that supports dynamic resolution across the vision tokenizer, MLLM, and diffusion decoder. This design allows for flexible and efficient context-aware image editing and generation across diverse tasks. ILLUME+ (3B) exhibits competitive performance against existing unified MLLMs and specialized models across multimodal understanding, generation, and editing benchmarks. With its strong performance, ILLUME+ provides a scalable and versatile foundation for future multimodal applications. Project Page: https://illume-unified-mllm.github.io/.
Authors: Hanyang Wang, Fangfu Liu, Jiawei Chi, Yueqi Duan
Abstract: Recovering 3D scenes from sparse views is a challenging task due to its inherent ill-posed problem. Conventional methods have developed specialized solutions (e.g., geometry regularization or feed-forward deterministic model) to mitigate the issue. However, they still suffer from performance degradation by minimal overlap across input views with insufficient visual information. Fortunately, recent video generative models show promise in addressing this challenge as they are capable of generating video clips with plausible 3D structures. Powered by large pretrained video diffusion models, some pioneering research start to explore the potential of video generative prior and create 3D scenes from sparse views. Despite impressive improvements, they are limited by slow inference time and the lack of 3D constraint, leading to inefficiencies and reconstruction artifacts that do not align with real-world geometry structure. In this paper, we propose VideoScene to distill the video diffusion model to generate 3D scenes in one step, aiming to build an efficient and effective tool to bridge the gap from video to 3D. Specifically, we design a 3D-aware leap flow distillation strategy to leap over time-consuming redundant information and train a dynamic denoising policy network to adaptively determine the optimal leap timestep during inference. Extensive experiments demonstrate that our VideoScene achieves faster and superior 3D scene generation results than previous video diffusion models, highlighting its potential as an efficient tool for future video to 3D applications. Project Page: https://hanyang-21.github.io/VideoScene
Authors: Shu-Wei Lu, Yi-Hsuan Tsai, Yi-Ting Chen
Abstract: Bird's-eye view (BEV) perception has gained significant attention because it provides a unified representation to fuse multiple view images and enables a wide range of down-stream autonomous driving tasks, such as forecasting and planning. Recent state-of-the-art models utilize projection-based methods which formulate BEV perception as query learning to bypass explicit depth estimation. While we observe promising advancements in this paradigm, they still fall short of real-world applications because of the lack of uncertainty modeling and expensive computational requirement. In this work, we introduce GaussianLSS, a novel uncertainty-aware BEV perception framework that revisits unprojection-based methods, specifically the Lift-Splat-Shoot (LSS) paradigm, and enhances them with depth un-certainty modeling. GaussianLSS represents spatial dispersion by learning a soft depth mean and computing the variance of the depth distribution, which implicitly captures object extents. We then transform the depth distribution into 3D Gaussians and rasterize them to construct uncertainty-aware BEV features. We evaluate GaussianLSS on the nuScenes dataset, achieving state-of-the-art performance compared to unprojection-based methods. In particular, it provides significant advantages in speed, running 2.5x faster, and in memory efficiency, using 0.3x less memory compared to projection-based methods, while achieving competitive performance with only a 0.4% IoU difference.
Authors: Chicago Y. Park, Weijie Gan, Zihao Zou, Yuyang Hu, Zhixin Sun, Ulugbek S. Kamilov
Abstract: Model-based deep learning (MBDL) is a powerful methodology for designing deep models to solve imaging inverse problems. MBDL networks can be seen as iterative algorithms that estimate the desired image using a physical measurement model and a learned image prior specified using a convolutional neural net (CNNs). The iterative nature of MBDL networks increases the test-time computational complexity, which limits their applicability in certain large-scale applications. Here we make two contributions to address this issue: First, we show how structured pruning can be adopted to reduce the number of parameters in MBDL networks. Second, we present three methods to fine-tune the pruned MBDL networks to mitigate potential performance loss. Each fine-tuning strategy has a unique benefit that depends on the presence of a pre-trained model and a high-quality ground truth. We show that our pruning and fine-tuning approach can accelerate image reconstruction using popular deep equilibrium learning (DEQ) and deep unfolding (DU) methods by 50% and 32%, respectively, with nearly no performance loss. This work thus offers a step forward for solving inverse problems by showing the potential of pruning to improve the scalability of MBDL. Code is available at https://github.com/wustl-cig/MBDL_Pruning .
Authors: Harshavardhana T. Gowda, Lee M. Miller
Abstract: $\textit{Objective.}$ In this article, we present data and methods for decoding hand gestures using surface electromyogram (EMG) signals. EMG-based upper limb interfaces are valuable for amputee rehabilitation, artificial supernumerary limb augmentation, gestural control of computers, and virtual and augmented reality applications. $\textit{Approach.}$ To achieve this, we collect EMG signals from the upper limb using surface electrodes placed at key muscle sites involved in hand movements. Additionally, we design and evaluate efficient models for decoding EMG signals. $\textit{Main results.}$ Our findings reveal that the manifold of symmetric positive definite (SPD) matrices serves as an effective embedding space for EMG signals. Moreover, for the first time, we quantify the distribution shift of these signals across individuals. $\textit{Significance.}$ Overall, our approach demonstrates significant potential for developing efficient and interpretable methods for decoding EMG signals. This is particularly important as we move toward the broader adoption of EMG-based wrist interfaces.
Authors: Luca Scimeca, Alexander Rubinstein, Damien Teney, Seong Joon Oh, Yoshua Bengio
Abstract: Spurious correlations in the data, where multiple cues are predictive of the target labels, often lead to a phenomenon known as shortcut learning, where a model relies on erroneous, easy-to-learn cues while ignoring reliable ones. In this work, we propose DiffDiv an ensemble diversification framework exploiting Diffusion Probabilistic Models (DPMs) to mitigate this form of bias. We show that at particular training intervals, DPMs can generate images with novel feature combinations, even when trained on samples displaying correlated input features. We leverage this crucial property to generate synthetic counterfactuals to increase model diversity via ensemble disagreement. We show that DPM-guided diversification is sufficient to remove dependence on shortcut cues, without a need for additional supervised signals. We further empirically quantify its efficacy on several diversification objectives, and finally show improved generalization and diversification on par with prior work that relies on auxiliary data collection.
Authors: Maximilian B\"other, Abraham Sebastian, Pranjal Awasthi, Ana Klimovic, Srikumar Ramalingam
Abstract: Modern datasets span billions of samples, making training on all available data infeasible. Selecting a high quality subset helps in reducing training costs and enhancing model quality. Submodularity, a discrete analogue of convexity, is commonly used for solving such subset selection problems. However, existing algorithms for optimizing submodular functions are sequential, and the prior distributed methods require at least one central machine to fit the target subset in DRAM. At billion datapoint scale, even the subset may not fit a single machine, and the sequential algorithms are prohibitively slow. In this paper, we relax the requirement of having a central machine for the target subset by proposing a novel distributed bounding algorithm with provable approximation guarantees. The algorithm iteratively bounds the minimum and maximum utility values to select high quality points and discard the unimportant ones. When bounding does not find the complete subset, we use a multi-round, partition-based distributed greedy algorithm to identify the remaining subset. We discuss how to implement these algorithms in a distributed data processing framework and empirically analyze different configurations. We find high quality subsets on CIFAR-100 and ImageNet with marginal or no loss in quality compared to centralized methods, and scale to a dataset with 13 billion points.
Authors: ZeMing Gong, Austin T. Wang, Xiaoliang Huo, Joakim Bruslund Haurum, Scott C. Lowe, Graham W. Taylor, Angel X. Chang
Abstract: Measuring biodiversity is crucial for understanding ecosystem health. While prior works have developed machine learning models for taxonomic classification of photographic images and DNA separately, in this work, we introduce a multimodal approach combining both, using CLIP-style contrastive learning to align images, barcode DNA, and text-based representations of taxonomic labels in a unified embedding space. This allows for accurate classification of both known and unknown insect species without task-specific fine-tuning, leveraging contrastive learning for the first time to fuse barcode DNA and image data. Our method surpasses previous single-modality approaches in accuracy by over 8% on zero-shot learning tasks, showcasing its effectiveness in biodiversity studies.
Authors: Emiel van Miltenburg
Abstract: This short position paper provides a manually curated list of non-English image captioning datasets (as of May 2024). Through this list, we can observe the dearth of datasets in different languages: only 23 different languages are represented. With the addition of the Crossmodal-3600 dataset (Thapliyal et al., 2022, 36 languages) this number increases somewhat, but still this number is small compared to the +/-500 institutional languages that are out there. This paper closes with some open questions for the field of Vision & Language.
Authors: Anirudh Mazumder, Jianguo Liu
Abstract: Lung diseases have become a prevalent problem throughout the United States, affecting over 34 million people. Accurate and timely diagnosis of the different types of lung diseases is critical, and Artificial Intelligence (AI) methods could speed up these processes. A dual-stage vision transformer is built throughout this research by integrating a Vision Transformer (ViT) and a Swin Transformer to classify 14 different lung diseases from X-ray scans of patients with these diseases. The proposed model achieved an accuracy of 92.06% on a label-level when making predictions on an unseen testing subset of the dataset after data preprocessing and training the neural network. The model showed promise for accurately classifying lung diseases and diagnosing patients who suffer from these harmful diseases.
Authors: Andreas Habring, Alexander Falk, Thomas Pock
Abstract: In this article we propose a novel method for sampling from Gibbs distributions of the form $\pi(x)\propto\exp(-U(x))$ with a potential $U(x)$. In particular, inspired by diffusion models we propose to consider a sequence $(\pi^{t_k})_k$ of approximations of the target density, for which $\pi^{t_k}\approx \pi$ for $k$ small and, on the other hand, $\pi^{t_k}$ exhibits favorable properties for sampling for $k$ large. This sequence is obtained by replacing parts of the potential $U$ by its Moreau envelopes. Sampling is performed in an Annealed Langevin type procedure, that is, sequentially sampling from $\pi^{t_k}$ for decreasing $k$, effectively guiding the samples from a simple starting density to the more complex target. In addition to a theoretical analysis we show experimental results supporting the efficacy of the method in terms of increased convergence speed and applicability to multi-modal densities $\pi$.
Authors: Xinkai Wang, Yue Yang, Kehong Zhou, Xue Xie, Lifeng Zhu, Aiguo Song, Bruce Daniel
Abstract: Chinese acupuncture practitioners primarily depend on muscle memory and tactile feedback to insert needles and accurately target acupuncture points, as the current workflow lacks imaging modalities and visual aids. Consequently, new practitioners often learn through trial and error, requiring years of experience to become proficient and earn the trust of patients. Medical students face similar challenges in mastering this skill. To address these challenges, we developed an innovative system, MRUCT, that integrates ultrasonic computed tomography (UCT) with mixed reality (MR) technology to visualize acupuncture points in real-time. This system offers offline image registration and real-time guidance during needle insertion, enabling them to accurately position needles based on anatomical structures such as bones, muscles, and auto-generated reference points, with the potential for clinical implementation. In this paper, we outline the non-rigid registration methods used to reconstruct anatomical structures from UCT data, as well as the key design considerations of the MR system. We evaluated two different 3D user interface (3DUI) designs and compared the performance of our system to traditional workflows for both new practitioners and medical students. The results highlight the potential of MR to enhance therapeutic medical practices and demonstrate the effectiveness of the system we developed.
Authors: Bowen Chen, Keyan Chen, Mohan Yang, Zhengxia Zou, Zhenwei Shi
Abstract: Remote sensing image super-resolution (SR) aims to reconstruct high-resolution remote sensing images from low-resolution inputs, thereby addressing limitations imposed by sensors and imaging conditions. However, the inherent characteristics of remote sensing images, including diverse ground object types and complex details, pose significant challenges to achieving high-quality reconstruction. Existing methods typically employ a uniform structure to process various types of ground objects without distinction, making it difficult to adapt to the complex characteristics of remote sensing images. To address this issue, we introduce a Mixture of Experts (MoE) model and design a set of heterogeneous experts. These experts are organized into multiple expert groups, where experts within each group are homogeneous while being heterogeneous across groups. This design ensures that specialized activation parameters can be employed to handle the diverse and intricate details of ground objects effectively. To better accommodate the heterogeneous experts, we propose a multi-level feature aggregation strategy to guide the routing process. Additionally, we develop a dual-routing mechanism to adaptively select the optimal expert for each pixel. Experiments conducted on the UCMerced and AID datasets demonstrate that our proposed method achieves superior SR reconstruction accuracy compared to state-of-the-art methods. The code will be available at https://github.com/Mr-Bamboo/MFG-HMoE.
Authors: Nam Anh Dinh, Itai Lang, Hyunwoo Kim, Oded Stein, Rana Hanocka
Abstract: We present Geometry in Style, a new method for identity-preserving mesh stylization. Existing techniques either adhere to the original shape through overly restrictive deformations such as bump maps or significantly modify the input shape using expressive deformations that may introduce artifacts or alter the identity of the source shape. In contrast, we represent a deformation of a triangle mesh as a target normal vector for each vertex neighborhood. The deformations we recover from target normals are expressive enough to enable detailed stylizations yet restrictive enough to preserve the shape's identity. We achieve such deformations using our novel differentiable As-Rigid-As-Possible (dARAP) layer, a neural-network-ready adaptation of the classical ARAP algorithm which we use to solve for per-vertex rotations and deformed vertices. As a differentiable layer, dARAP is paired with a visual loss from a text-to-image model to drive deformations toward style prompts, altogether giving us Geometry in Style. Our project page is at https://threedle.github.io/geometry-in-style.
Authors: Alice E. A. Allen, Emily Shinkle, Roxana Bujack, Nicholas Lubbers
Abstract: The representation of atomic configurations for machine learning models has led to the development of numerous descriptors, often to describe the local environment of atoms. However, many of these representations are incomplete and/or functionally dependent. Incomplete descriptor sets are unable to represent all meaningful changes in the atomic environment. Complete constructions of atomic environment descriptors, on the other hand, often suffer from a high degree of functional dependence, where some descriptors can be written as functions of the others. These redundant descriptors do not provide additional power to discriminate between different atomic environments and increase the computational burden. By employing techniques from the pattern recognition literature to existing atomistic representations, we remove descriptors that are functions of other descriptors to produce the smallest possible set that satisfies completeness. We apply this in two ways: first we refine an existing description, the Atomistic Cluster Expansion. We show that this yields a more efficient subset of descriptors. Second, we augment an incomplete construction based on a scalar neural network, yielding a new message-passing network architecture that can recognize up to 5-body patterns in each neuron by taking advantage of an optimal set of Cartesian tensor invariants. This architecture shows strong accuracy on state-of-the-art benchmarks while retaining low computational cost. Our results not only yield improved models, but point the way to classes of invariant bases that minimize cost while maximizing expressivity for a host of applications.