Authors: Saptarshi Banerjee, Tausif Mallick, Amlan Chakroborty, Himadri Nath Saha, Nityananda T. Takur
Abstract: Addressing plant diseases and pests is critical for enhancing crop production and preventing economic losses. Recent advances in artificial intelligence (AI), machine learning (ML), and deep learning (DL) have significantly improved the precision and efficiency of detection methods, surpassing the limitations of manual identification. This study reviews modern computer-based techniques for detecting plant diseases and pests from images, including recent AI developments. The methodologies are organized into five categories: hyperspectral imaging, non-visualization techniques, visualization approaches, modified deep learning architectures, and transformer models. This structured taxonomy provides researchers with detailed, actionable insights for selecting advanced state-of-the-art detection methods. A comprehensive survey of recent work and comparative studies demonstrates the consistent superiority of modern AI-based approaches, which often outperform older image analysis methods in speed and accuracy. In particular, vision transformers such as the Hierarchical Vision Transformer (HvT) have shown accuracy exceeding 99.3% in plant disease detection, outperforming architectures like MobileNetV3. The study concludes by discussing system design challenges, proposing solutions, and outlining promising directions for future research.
Authors: Yuqin He, Tengfei Ma, Chaoyi Li, Pengsen Ma, Hongxin Xiang, Jianmin Wang, Yiping Liu, Bosheng Song, Xiangxiang Zeng
Abstract: To mitigate the potential adverse health effects of simultaneous multi-drug use, including unexpected side effects and interactions, accurately identifying and predicting drug-drug interactions (DDIs) is considered a crucial task in the field of deep learning. Although existing methods have demonstrated promising performance, they suffer from the bottleneck of limited functional motif-based representation learning, as DDIs are fundamentally caused by motif interactions rather than the overall drug structures. In this paper, we propose an Image-enhanced molecular motif sequence representation framework for \textbf{DDI} prediction, called ImageDDI, which represents a pair of drugs from both global and local structures. Specifically, ImageDDI tokenizes molecules into functional motifs. To effectively represent a drug pair, their motifs are combined into a single sequence and embedded using a transformer-based encoder, starting from the local structure representation. By leveraging the associations between drug pairs, ImageDDI further enhances the spatial representation of molecules using global molecular image information (e.g. texture, shadow, color, and planar spatial relationships). To integrate molecular visual information into functional motif sequence, ImageDDI employs Adaptive Feature Fusion, enhancing the generalization of ImageDDI by dynamically adapting the fusion process of feature representations. Experimental results on widely used datasets demonstrate that ImageDDI outperforms state-of-the-art methods. Moreover, extensive experiments show that ImageDDI achieved competitive performance in both 2D and 3D image-enhanced scenarios compared to other models.
Authors: Christophe EL Zeinaty, Wassim Hamidouche, Glenn Herrou, Daniel Menard
Abstract: Object detection (OD) has become vital for numerous computer vision applications, but deploying it on resource-constrained IoT devices presents a significant challenge. These devices, often powered by energy-efficient microcontrollers, struggle to handle the computational load of deep learning-based OD models. This issue is compounded by the rapid proliferation of IoT devices, predicted to surpass 150 billion by 2030. TinyML offers a compelling solution by enabling OD on ultra-low-power devices, paving the way for efficient and real-time processing at the edge. Although numerous survey papers have been published on this topic, they often overlook the optimization challenges associated with deploying OD models in TinyML environments. To address this gap, this survey paper provides a detailed analysis of key optimization techniques for deploying OD models on resource-constrained devices. These techniques include quantization, pruning, knowledge distillation, and neural architecture search. Furthermore, we explore both theoretical approaches and practical implementations, bridging the gap between academic research and real-world edge artificial intelligence deployment. Finally, we compare the key performance indicators (KPIs) of existing OD implementations on microcontroller devices, highlighting the achieved maturity level of these solutions in terms of both prediction accuracy and efficiency. We also provide a public repository to continually track developments in this fast-evolving field: https://github.com/christophezei/Optimizing-Object-Detection-Models-for-TinyML-A-Comprehensive-Survey.
Authors: Jinlin Xiang, Minho Choi, Yubo Zhang, Zhihao Zhou, Arka Majumdar, Eli Shlizerman
Abstract: Hybrid Optical Neural Networks (ONNs, typically consisting of an optical frontend and a digital backend) offer an energy-efficient alternative to fully digital deep networks for real-time, power-constrained systems. However, their adoption is limited by two main challenges: the accuracy gap compared to large-scale networks during training, and discrepancies between simulated and fabricated systems that further degrade accuracy. While previous work has proposed end-to-end optimizations for specific datasets (e.g., MNIST) and optical systems, these approaches typically lack generalization across tasks and hardware designs. To address these limitations, we propose a task-agnostic and hardware-agnostic pipeline that supports image classification and segmentation across diverse optical systems. To assist optical system design before training, we estimate achievable model accuracy based on user-specified constraints such as physical size and the dataset. For training, we introduce Neural Tangent Knowledge Distillation (NTKD), which aligns optical models with electronic teacher networks, thereby narrowing the accuracy gap. After fabrication, NTKD also guides fine-tuning of the digital backend to compensate for implementation errors. Experiments on multiple datasets (e.g., MNIST, CIFAR, Carvana Masking) and hardware configurations show that our pipeline consistently improves ONN performance and enables practical deployment in both pre-fabrication simulations and physical implementations.
Authors: Qian Wang, Ziqi Huang, Ruoxi Jia, Paul Debevec, Ning Yu
Abstract: Despite recent advances, long-sequence video generation frameworks still suffer from significant limitations: poor assistive capability, suboptimal visual quality, and limited expressiveness. To mitigate these limitations, we propose MAViS, an end-to-end multi-agent collaborative framework for long-sequence video storytelling. MAViS orchestrates specialized agents across multiple stages, including script writing, shot designing, character modeling, keyframe generation, video animation, and audio generation. In each stage, agents operate under the 3E Principle -- Explore, Examine, and Enhance -- to ensure the completeness of intermediate outputs. Considering the capability limitations of current generative models, we propose the Script Writing Guidelines to optimize compatibility between scripts and generative tools. Experimental results demonstrate that MAViS achieves state-of-the-art performance in assistive capability, visual quality, and video expressiveness. Its modular framework further enables scalability with diverse generative models and tools. With just a brief user prompt, MAViS is capable of producing high-quality, expressive long-sequence video storytelling, enriching inspirations and creativity for users. To the best of our knowledge, MAViS is the only framework that provides multimodal design output -- videos with narratives and background music.
Authors: Ankan Deria, Dwarikanath Mahapatra, Behzad Bozorgtabar, Mohna Chakraborty, Snehashis Chakraborty, Sudipta Roy
Abstract: Virtual try-on seeks to generate photorealistic images of individuals in desired garments, a task that must simultaneously preserve personal identity and garment fidelity for practical use in fashion retail and personalization. However, existing methods typically handle upper and lower garments separately, rely on heavy preprocessing, and often fail to preserve person-specific cues such as tattoos, accessories, and body shape-resulting in limited realism and flexibility. To this end, we introduce MuGa-VTON, a unified multi-garment diffusion framework that jointly models upper and lower garments together with person identity in a shared latent space. Specifically, we proposed three key modules: the Garment Representation Module (GRM) for capturing both garment semantics, the Person Representation Module (PRM) for encoding identity and pose cues, and the A-DiT fusion module, which integrates garment, person, and text-prompt features through a diffusion transformer. This architecture supports prompt-based customization, allowing fine-grained garment modifications with minimal user input. Extensive experiments on the VITON-HD and DressCode benchmarks demonstrate that MuGa-VTON outperforms existing methods in both qualitative and quantitative evaluations, producing high-fidelity, identity-preserving results suitable for real-world virtual try-on applications.
Authors: Aneel Damaraju, Dean Hazineh, Todd Zickler
Abstract: Vision benefits from grouping pixels into objects and understanding their spatial relationships, both laterally and in depth. We capture this with a scene representation comprising an occlusion-ordered stack of "object layers," each containing an isolated and amodally-completed object. To infer this representation from an image, we introduce a diffusion-based architecture named Concurrent Object Layers (CObL). CObL generates a stack of object layers in parallel, using Stable Diffusion as a prior for natural objects and inference-time guidance to ensure the inferred layers composite back to the input image. We train CObL using a few thousand synthetically-generated images of multi-object tabletop scenes, and we find that it zero-shot generalizes to photographs of real-world tabletops with varying numbers of novel objects. In contrast to recent models for amodal object completion, CObL reconstructs multiple occluded objects without user prompting and without knowing the number of objects beforehand. Unlike previous models for unsupervised object-centric representation learning, CObL is not limited to the world it was trained in.
Authors: Aaditya Baranwal, Madhav Kataria, Naitik Agrawal, Yogesh S Rawat, Shruti Vyas
Abstract: Current Vision Language Models (VLMs) demonstrate a critical gap between surface-level recognition and deep narrative reasoning when processing sequential visual storytelling. Through a comprehensive investigation of manga narrative understanding, we reveal that while recent large multimodal models excel at individual panel interpretation, they systematically fail at temporal causality and cross-panel cohesion, core requirements for coherent story comprehension. We introduce a novel evaluation framework that combines fine-grained multimodal annotation, cross-modal embedding analysis, and retrieval-augmented assessment to systematically characterize these limitations. Our methodology includes (i) a rigorous annotation protocol linking visual elements to narrative structure through aligned light novel text, (ii) comprehensive evaluation across multiple reasoning paradigms, including direct inference and retrieval-augmented generation, and (iii) cross-modal similarity analysis revealing fundamental misalignments in current VLMs' joint representations. Applying this framework to Re:Zero manga across 11 chapters with 308 annotated panels, we conduct the first systematic study of long-form narrative understanding in VLMs through three core evaluation axes: generative storytelling, contextual dialogue grounding, and temporal reasoning. Our findings demonstrate that current models lack genuine story-level intelligence, struggling particularly with non-linear narratives, character consistency, and causal inference across extended sequences. This work establishes both the foundation and practical methodology for evaluating narrative intelligence, while providing actionable insights into the capability of deep sequential understanding of Discrete Visual Narratives beyond basic recognition in Multimodal Models.
Authors: Mansi Phute (Georgia Tech), Ravikumar Balakrishnan (HiddenLayer)
Abstract: Vision Language Models (VLMs) are increasingly being used in a broad range of applications, bringing their security and behavioral control to the forefront. While existing approaches for behavioral control or output redirection, like system prompting in VLMs, are easily detectable and often ineffective, activation-based steering vectors require invasive runtime access to model internals--incompatible with API-based services and closed-source deployments. We introduce VISOR (Visual Input-based Steering for Output Redirection), a novel method that achieves sophisticated behavioral control through optimized visual inputs alone. By crafting universal steering images that induce target activation patterns, VISOR enables practical deployment across all VLM serving modalities while remaining imperceptible compared to explicit textual instructions. We validate VISOR on LLaVA-1.5-7B across three critical alignment tasks: refusal, sycophancy and survival instinct. A single 150KB steering image matches steering vector performance within 1-2% for positive behavioral shifts while dramatically exceeding it for negative steering--achieving up to 25% shifts from baseline compared to steering vectors' modest changes. Unlike system prompting (3-4% shifts), VISOR provides robust bidirectional control while maintaining 99.9% performance on 14,000 unrelated MMLU tasks. Beyond eliminating runtime overhead and model access requirements, VISOR exposes a critical security vulnerability: adversaries can achieve sophisticated behavioral manipulation through visual channels alone, bypassing text-based defenses. Our work fundamentally re-imagines multimodal model control and highlights the urgent need for defenses against visual steering attacks.
Authors: Anh Le, Asanobu Kitamoto
Abstract: Kindai documents, written in modern Japanese from the late 19th to early 20th century, hold significant historical value for researchers studying societal structures, daily life, and environmental conditions of that period. However, transcribing these documents remains a labor-intensive and time-consuming task, resulting in limited annotated data for training optical character recognition (OCR) systems. This research addresses this challenge of data scarcity by leveraging parallel textline images - pairs of original Kindai text and their counterparts in contemporary Japanese fonts - to augment training datasets. We introduce a distance-based objective function that minimizes the gap between self-attention features of the parallel image pairs. Specifically, we explore Euclidean distance and Maximum Mean Discrepancy (MMD) as domain adaptation metrics. Experimental results demonstrate that our method reduces the character error rate (CER) by 2.23% and 3.94% over a Transformer-based OCR baseline when using Euclidean distance and MMD, respectively. Furthermore, our approach improves the discriminative quality of self-attention representations, leading to more effective OCR performance for historical documents.
Authors: Wenhao Liang, Wei Emma Zhang, Lin Yue, Miao Xu, Olaf Maennel, Weitong Chen
Abstract: Probability calibration is critical when Vision Transformers are deployed in risk-sensitive applications. The standard fix, post-hoc temperature scaling, uses a single global scalar and requires a held-out validation set. We introduce Calibration Attention (CalAttn), a drop-in module that learns an adaptive, per-instance temperature directly from the ViT's CLS token. Across CIFAR-10/100, MNIST, Tiny-ImageNet, and ImageNet-1K, CalAttn reduces calibration error by up to 4x on ViT-224, DeiT, and Swin, while adding under 0.1 percent additional parameters. The learned temperatures cluster tightly around 1.0, in contrast to the large global values used by standard temperature scaling. CalAttn is simple, efficient, and architecture-agnostic, and yields more trustworthy probabilities without sacrificing accuracy. Code: [https://github.com/EagleAdelaide/CalibrationAttention-CalAttn-](https://github.com/EagleAdelaide/CalibrationAttention-CalAttn-)
Authors: Wei Li, Pengcheng Zhou, Linye Ma, Wenyi Zhao, Huihua Yang
Abstract: Both limited annotation and domain shift are significant challenges frequently encountered in medical image segmentation, leading to derivative scenarios like semi-supervised medical (SSMIS), semi-supervised medical domain generalization (Semi-MDG) and unsupervised medical domain adaptation (UMDA). Conventional methods are generally tailored to specific tasks in isolation, the error accumulation hinders the effective utilization of unlabeled data and limits further improvements, resulting in suboptimal performance when these issues occur. In this paper, we aim to develop a generic framework that masters all three tasks. We found that the key to solving the problem lies in how to generate reliable pseudo labels for the unlabeled data in the presence of domain shift with labeled data and increasing the diversity of the model. To tackle this issue, we employ a Diverse Teaching and Label Propagation Network (DTLP-Net) to boosting the Generic Semi-Supervised Medical Image Segmentation. Our DTLP-Net involves a single student model and two diverse teacher models, which can generate reliable pseudo-labels for the student model. The first teacher model decouple the training process with labeled and unlabeled data, The second teacher is momentum-updated periodically, thus generating reliable yet divers pseudo-labels. To fully utilize the information within the data, we adopt inter-sample and intra-sample data augmentation to learn the global and local knowledge. In addition, to further capture the voxel-level correlations, we propose label propagation to enhance the model robust. We evaluate our proposed framework on five benchmark datasets for SSMIS, UMDA, and Semi-MDG tasks. The results showcase notable improvements compared to state-of-the-art methods across all five settings, indicating the potential of our framework to tackle more challenging SSL scenarios.
Authors: Yunqi Miao, Zhiyu Qu, Mingqi Gao, Changrui Chen, Jifei Song, Jungong Han, Jiankang Deng
Abstract: Although diffusion prior is rising as a powerful solution for blind face restoration (BFR), the inherent gap between the vanilla diffusion model and BFR settings hinders its seamless adaptation. The gap mainly stems from the discrepancy between 1) high-quality (HQ) and low-quality (LQ) images and 2) synthesized and real-world images. The vanilla diffusion model is trained on images with no or less degradations, whereas BFR handles moderately to severely degraded images. Additionally, LQ images used for training are synthesized by a naive degradation model with limited degradation patterns, which fails to simulate complex and unknown degradations in real-world scenarios. In this work, we use a unified network FLIPNET that switches between two modes to resolve specific gaps. In Restoration mode, the model gradually integrates BFR-oriented features and face embeddings from LQ images to achieve authentic and faithful face restoration. In Degradation mode, the model synthesizes real-world like degraded images based on the knowledge learned from real-world degradation datasets. Extensive evaluations on benchmark datasets show that our model 1) outperforms previous diffusion prior based BFR methods in terms of authenticity and fidelity, and 2) outperforms the naive degradation model in modeling the real-world degradations.
Authors: Tuo Liu, Qinghan Yang, Yu Zhang, Rongjun Ge, Yang Chen, Guangquan Zhou
Abstract: Left ventricular (LV) indicator measurements following clinical echocardiog-raphy guidelines are important for diagnosing cardiovascular disease. Alt-hough existing algorithms have explored automated LV quantification, they can struggle to capture generic visual representations due to the normally small training datasets. Therefore, it is necessary to introduce vision founda-tional models (VFM) with abundant knowledge. However, VFMs represented by the segment anything model (SAM) are usually suitable for segmentation but incapable of identifying key anatomical points, which are critical in LV indicator measurements. In this paper, we propose a novel framework named AutoSAME, combining the powerful visual understanding of SAM with seg-mentation and landmark localization tasks simultaneously. Consequently, the framework mimics the operation of cardiac sonographers, achieving LV indi-cator measurements consistent with clinical guidelines. We further present fil-tered cross-branch attention (FCBA) in AutoSAME, which leverages relatively comprehensive features in the segmentation to enhance the heatmap regression (HR) of key points from the frequency domain perspective, optimizing the vis-ual representation learned by the latter. Moreover, we propose spatial-guided prompt alignment (SGPA) to automatically generate prompt embeddings guid-ed by spatial properties of LV, thereby improving the accuracy of dense pre-dictions by prior spatial knowledge. The extensive experiments on an echocar-diography dataset demonstrate the efficiency of each design and the superiori-ty of our AutoSAME in LV segmentation, landmark localization, and indicator measurements. The code will be available at https://github.com/QC-LIU-1997/AutoSAME.
Authors: Chenruo Liu, Hongjun Liu, Zeyu Lai, Yiqiu Shen, Chen Zhao, Qi Lei
Abstract: To enhance group robustness to spurious correlations, prior work often relies on auxiliary annotations for groups or spurious features and assumes identical sets of groups across source and target domains. These two requirements are both unnatural and impractical in real-world settings. To overcome these limitations, we propose a method that leverages the semantic structure inherent in class labels--specifically, superclass information--to naturally reduce reliance on spurious features. Our model employs gradient-based attention guided by a pre-trained vision-language model to disentangle superclass-relevant and irrelevant features. Then, by promoting the use of all superclass-relevant features for prediction, our approach achieves robustness to more complex spurious correlations without the need to annotate any source samples. Experiments across diverse datasets demonstrate that our method significantly outperforms baselines in domain generalization tasks, with clear improvements in both quantitative metrics and qualitative visualizations.
Authors: Jingyun Liang, Jingkai Zhou, Shikai Li, Chenjie Cao, Lei Sun, Yichen Qian, Weihua Chen, Fan Wang
Abstract: Generating human videos with realistic and controllable motions is a challenging task. While existing methods can generate visually compelling videos, they lack separate control over four key video elements: foreground subject, background video, human trajectory and action patterns. In this paper, we propose a decomposed human motion control and video generation framework that explicitly decouples motion from appearance, subject from background, and action from trajectory, enabling flexible mix-and-match composition of these elements. Concretely, we first build a ground-aware 3D world coordinate system and perform motion editing directly in the 3D space. Trajectory control is implemented by unprojecting edited 2D trajectories into 3D with focal-length calibration and coordinate transformation, followed by speed alignment and orientation adjustment; actions are supplied by a motion bank or generated via text-to-motion methods. Then, based on modern text-to-video diffusion transformer models, we inject the subject as tokens for full attention, concatenate the background along the channel dimension, and add motion (trajectory and action) control signals by addition. Such a design opens up the possibility for us to generate realistic videos of anyone doing anything anywhere. Extensive experiments on benchmark datasets and real-world cases demonstrate that our method achieves state-of-the-art performance on both element-wise controllability and overall video quality.
Authors: Wenwen Yu, Zhibo Yang, Yuliang Liu, Xiang Bai
Abstract: Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities in document understanding. However, their reasoning processes remain largely black-box, making it difficult to ensure reliability and trustworthiness, especially in high-stakes domains such as legal, financial, and medical document analysis. Existing methods use fixed Chain-of-Thought (CoT) reasoning with supervised fine-tuning (SFT) but suffer from catastrophic forgetting, poor adaptability, and limited generalization across domain tasks. In this paper, we propose DocThinker, a rule-based Reinforcement Learning (RL) framework for dynamic inference-time reasoning. Instead of relying on static CoT templates, DocThinker autonomously refines reasoning strategies via policy learning, generating explainable intermediate results, including structured reasoning processes, rephrased questions, regions of interest (RoI) supporting the answer, and the final answer. By integrating multi-objective rule-based rewards and KL-constrained optimization, our method mitigates catastrophic forgetting and enhances both adaptability and transparency. Extensive experiments on multiple benchmarks demonstrate that DocThinker significantly improves generalization while producing more explainable and human-understandable reasoning steps. Our findings highlight RL as a powerful alternative for enhancing explainability and adaptability in MLLM-based document understanding. Code will be available at https://github.com/wenwenyu/DocThinker.
Authors: Yuxiao Wang, Wolin Liang, Yu Lei, Weiying Xue, Nan Zhuang, Qi Liu
Abstract: Human-Object Interaction (HOI) detection aims to localize human-object pairs and recognize their interactions in images. Although DETR-based methods have recently emerged as the mainstream framework for HOI detection, they still suffer from a key limitation: Randomly initialized queries lack explicit semantics, leading to suboptimal detection performance. To address this challenge, we propose QueryCraft, a novel plug-and-play HOI detection framework that incorporates semantic priors and guided feature learning through transformer-based query initialization. Central to our approach is \textbf{ACTOR} (\textbf{A}ction-aware \textbf{C}ross-modal \textbf{T}ransf\textbf{OR}mer), a cross-modal Transformer encoder that jointly attends to visual regions and textual prompts to extract action-relevant features. Rather than merely aligning modalities, ACTOR leverages language-guided attention to infer interaction semantics and produce semantically meaningful query representations. To further enhance object-level query quality, we introduce a \textbf{P}erceptual \textbf{D}istilled \textbf{Q}uery \textbf{D}ecoder (\textbf{PDQD}), which distills object category awareness from a pre-trained detector to serve as object query initiation. This dual-branch query initialization enables the model to generate more interpretable and effective queries for HOI detection. Extensive experiments on HICO-Det and V-COCO benchmarks demonstrate that our method achieves state-of-the-art performance and strong generalization. Code will be released upon publication.
Authors: Deheng Ye, Fangyun Zhou, Jiacheng Lv, Jianqi Ma, Jun Zhang, Junyan Lv, Junyou Li, Minwen Deng, Mingyu Yang, Qiang Fu, Wei Yang, Wenkai Lv, Yangbin Yu, Yewen Wang, Yonghang Guan, Zhihao Hu, Zhongbin Fang, Zhongqian Sun
Abstract: We present Yan, a foundational framework for interactive video generation, covering the entire pipeline from simulation and generation to editing. Specifically, Yan comprises three core modules. AAA-level Simulation: We design a highly-compressed, low-latency 3D-VAE coupled with a KV-cache-based shift-window denoising inference process, achieving real-time 1080P/60FPS interactive simulation. Multi-Modal Generation: We introduce a hierarchical autoregressive caption method that injects game-specific knowledge into open-domain multi-modal video diffusion models (VDMs), then transforming the VDM into a frame-wise, action-controllable, real-time infinite interactive video generator. Notably, when the textual and visual prompts are sourced from different domains, the model demonstrates strong generalization, allowing it to blend and compose the style and mechanics across domains flexibly according to user prompts. Multi-Granularity Editing: We propose a hybrid model that explicitly disentangles interactive mechanics simulation from visual rendering, enabling multi-granularity video content editing during interaction through text. Collectively, Yan offers an integration of these modules, pushing interactive video generation beyond isolated capabilities toward a comprehensive AI-driven interactive creation paradigm, paving the way for the next generation of creative tools, media, and entertainment. The project page is: https://greatx3.github.io/Yan/.
Authors: Jihwan Park, Taehoon song, Sanghyeok Lee, Miso Choi, Hyunwoo J. Kim
Abstract: Vision-Language Models (VLMs) have been widely used in various visual recognition tasks due to their remarkable generalization capabilities. As these models grow in size and complexity, fine-tuning becomes costly, emphasizing the need to reuse adaptation knowledge from 'weaker' models to efficiently enhance 'stronger' ones. However, existing adaptation transfer methods exhibit limited transferability across models due to their model-specific design and high computational demands. To tackle this, we propose Transferable Model-agnostic adapter (TransMiter), a light-weight adapter that improves vision-language models 'without backpropagation'. TransMiter captures the knowledge gap between pre-trained and fine-tuned VLMs, in an 'unsupervised' manner. Once trained, this knowledge can be seamlessly transferred across different models without the need for backpropagation. Moreover, TransMiter consists of only a few layers, inducing a negligible additional inference cost. Notably, supplementing the process with a few labeled data further yields additional performance gain, often surpassing a fine-tuned stronger model, with a marginal training cost. Experimental results and analyses demonstrate that TransMiter effectively and efficiently transfers adaptation knowledge while preserving generalization abilities across VLMs of different sizes and architectures in visual recognition tasks.
Authors: Honglei Xu, Zhilu Zhang, Junjie Fan, Xiaohe Wu, Wangmeng Zuo
Abstract: Shooting video with a handheld mobile phone, the most common photographic device, often results in blurry frames due to shaking hands and other instability factors. Although previous video deblurring methods have achieved impressive progress, they still struggle to perform satisfactorily on real-world handheld video due to the blur domain gap between training and testing data. To address the issue, we propose a self-supervised method for handheld video deblurring, which is driven by sharp clues in the video. First, to train the deblurring model, we extract the sharp clues from the video and take them as misalignment labels of neighboring blurry frames. Second, to improve the model's ability, we propose a novel Self-Enhanced Video Deblurring (SEVD) method to create higher-quality paired video data. Third, we propose a Self-Constrained Spatial Consistency Maintenance (SCSCM) method to regularize the model, preventing position shifts between the output and input frames. Moreover, we construct a synthetic and a real-world handheld video dataset for handheld video deblurring. Extensive experiments on these two and other common real-world datasets demonstrate that our method significantly outperforms existing self-supervised ones. The code and datasets are publicly available at https://github.com/cshonglei/SelfHVD.
Authors: Justin London
Abstract: Neural artistic style transfers and blends the content and style representation of one image with the style of another. This enables artists to create unique innovative visuals and enhances artistic expression in various fields including art, design, and film. Color transfer algorithms are an important in digital image processing by adjusting the color information in a target image based on the colors in the source image. Color transfer enhances images and videos in film and photography, and can aid in image correction. We introduce a methodology that combines neural artistic style with color transfer. The method uses the Kullback-Leibler (KL) divergence to quantitatively evaluate color and luminance histogram matching algorithms including Reinhard global color transfer, iteration distribution transfer (IDT), IDT with regrain, Cholesky, and PCA between the original and neural artistic style transferred image using deep learning. We estimate the color channel kernel densities. Various experiments are performed to evaluate the KL of these algorithms and their color histograms for style to content transfer.
Authors: Jiahua Dong, Hui Yin, Wenqi Liang, Hanbin Zhao, Henghui Ding, Nicu Sebe, Salman Khan, Fahad Shahbaz Khan
Abstract: Video instance segmentation (VIS) has gained significant attention for its capability in tracking and segmenting object instances across video frames. However, most of the existing VIS approaches unrealistically assume that the categories of object instances remain fixed over time. Moreover, they experience catastrophic forgetting of old classes when required to continuously learn object instances belonging to new categories. To resolve these challenges, we develop a novel Hierarchical Visual Prompt Learning (HVPL) model that overcomes catastrophic forgetting of previous categories from both frame-level and video-level perspectives. Specifically, to mitigate forgetting at the frame level, we devise a task-specific frame prompt and an orthogonal gradient correction (OGC) module. The OGC module helps the frame prompt encode task-specific global instance information for new classes in each individual frame by projecting its gradients onto the orthogonal feature space of old classes. Furthermore, to address forgetting at the video level, we design a task-specific video prompt and a video context decoder. This decoder first embeds structural inter-class relationships across frames into the frame prompt features, and then propagates task-specific global video contexts from the frame prompt features to the video prompt. Through rigorous comparisons, our HVPL model proves to be more effective than baseline approaches. The code is available at https://github.com/JiahuaDong/HVPL.
Authors: Guiming Cao, Yuming Ou
Abstract: Knowledge distillation is a long-established technique for knowledge transfer, and has regained attention in the context of the recent emergence of large vision-language models (VLMs). However, vision-language knowledge distillation often requires sufficient training data to achieve robust generalization on amples with ambiguous or boundary-adjacent representations, which are associated with high predictive uncertainty. Critically, collecting such large-scale, task-specific data for training is often impractical in real-world scenarios. To address this major challenge arising from the entanglement of uncertainty and cross-modal feature representation, we propose Aligned Manifold Entropy for Robust Vision-Language Distillation (AME), aiming to achieve robust generalization under real-world conditions. AME applies entropy minimization over a reconfigured shared manifold, where multi-modal data (i.e., image and text) are bridged through a pair of projection functions, conducive to structural compression for cross-modal feature representations. This enables robust knowledge distillation under low-data regimes, while requiring no architectural modifications to the backbone. As a result, it can serve as a plug-and-play module compatible with a wide range of vision-language distillation frameworks. Notably, our theoretical analysis reveals that integrating knowledge distillation with entropy minimization over the shared manifold leads to a tighter generalization error bound. Extensive experiments across diverse distillation architectures and training settings demonstrate that AME consistently facilitates robust knowledge distillation, resulting in superior generalization performance across a wide spectrum of downstream tasks.
Authors: Xin Wang, Yin Guo, Jiamin Xia, Kaiyu Zhang, Niranjan Balu, Mahmud Mossa-Basha, Linda Shapiro, Chun Yuan
Abstract: Most prior unsupervised domain adaptation approaches for medical image segmentation are narrowly tailored to either the source-accessible setting, where adaptation is guided by source-target alignment, or the source-free setting, which typically resorts to implicit supervision mechanisms such as pseudo-labeling and model distillation. This substantial divergence in methodological designs between the two settings reveals an inherent flaw: the lack of an explicit, structured construction of anatomical knowledge that naturally generalizes across domains and settings. To bridge this longstanding divide, we introduce a unified, semantically grounded framework that supports both source-accessible and source-free adaptation. Fundamentally distinct from all prior works, our framework's adaptability emerges naturally as a direct consequence of the model architecture, without the need for any handcrafted adaptation strategies. Specifically, our model learns a domain-agnostic probabilistic manifold as a global space of anatomical regularities, mirroring how humans establish visual understanding. Thus, the structural content in each image can be interpreted as a canonical anatomy retrieved from the manifold and a spatial transformation capturing individual-specific geometry. This disentangled, interpretable formulation enables semantically meaningful prediction with intrinsic adaptability. Extensive experiments on challenging cardiac and abdominal datasets show that our framework achieves state-of-the-art results in both settings, with source-free performance closely approaching its source-accessible counterpart, a level of consistency rarely observed in prior works. Beyond quantitative improvement, we demonstrate strong interpretability of the proposed framework via manifold traversal for smooth shape manipulation.
Authors: Ke Liu, Xuanhan Wang, Qilong Zhang, Lianli Gao, Jingkuan Song
Abstract: Deep image watermarking, which refers to enable imperceptible watermark embedding and reliable extraction in cover images, has shown to be effective for copyright protection of image assets. However, existing methods face limitations in simultaneously satisfying three essential criteria for generalizable watermarking: 1) invisibility (imperceptible hide of watermarks), 2) robustness (reliable watermark recovery under diverse conditions), and 3) broad applicability (low latency in watermarking process). To address these limitations, we propose a Hierarchical Watermark Learning (HiWL), a two-stage optimization that enable a watermarking model to simultaneously achieve three criteria. In the first stage, distribution alignment learning is designed to establish a common latent space with two constraints: 1) visual consistency between watermarked and non-watermarked images, and 2) information invariance across watermark latent representations. In this way, multi-modal inputs including watermark message (binary codes) and cover images (RGB pixels) can be well represented, ensuring the invisibility of watermarks and robustness in watermarking process thereby. The second stage employs generalized watermark representation learning to establish a disentanglement policy for separating watermarks from image content in RGB space. In particular, it strongly penalizes substantial fluctuations in separated RGB watermarks corresponding to identical messages. Consequently, HiWL effectively learns generalizable latent-space watermark representations while maintaining broad applicability. Extensive experiments demonstrate the effectiveness of proposed method. In particular, it achieves 7.6\% higher accuracy in watermark extraction than existing methods, while maintaining extremely low latency (100K images processed in 8s).
Authors: Tao Luo, Weihua Xu
Abstract: Multimodal medical image fusion (MMIF) aims to integrate images from different modalities to produce a comprehensive image that enhances medical diagnosis by accurately depicting organ structures, tissue textures, and metabolic information. Capturing both the unique and complementary information across multiple modalities simultaneously is a key research challenge in MMIF. To address this challenge, this paper proposes a novel image fusion method, MMIF-AMIN, which features a new architecture that can effectively extract these unique and complementary features. Specifically, an Invertible Dense Network (IDN) is employed for lossless feature extraction from individual modalities. To extract complementary information between modalities, a Multi-scale Complementary Feature Extraction Module (MCFEM) is designed, which incorporates a hybrid attention mechanism, convolutional layers of varying sizes, and Transformers. An adaptive loss function is introduced to guide model learning, addressing the limitations of traditional manually-designed loss functions and enhancing the depth of data mining. Extensive experiments demonstrate that MMIF-AMIN outperforms nine state-of-the-art MMIF methods, delivering superior results in both quantitative and qualitative analyses. Ablation experiments confirm the effectiveness of each component of the proposed method. Additionally, extending MMIF-AMIN to other image fusion tasks also achieves promising performance.
Authors: Yimeng Geng, Mingyang Zhao, Fan Xu, Guanglin Cao, Gaofeng Meng, Hongbin Liu
Abstract: Ultrasound deformable registration estimates spatial transformations between pairs of deformed ultrasound images, which is crucial for capturing biomechanical properties and enhancing diagnostic accuracy in diseases such as thyroid nodules and breast cancer. However, ultrasound deformable registration remains highly challenging, especially under large deformation. The inherently low contrast, heavy noise and ambiguous tissue boundaries in ultrasound images severely hinder reliable feature extraction and correspondence matching. Existing methods often suffer from poor anatomical alignment and lack physical interpretability. To address the problem, we propose PADReg, a physics-aware deformable registration framework guided by contact force. PADReg leverages synchronized contact force measured by robotic ultrasound systems as a physical prior to constrain the registration. Specifically, instead of directly predicting deformation fields, we first construct a pixel-wise stiffness map utilizing the multi-modal information from contact force and ultrasound images. The stiffness map is then combined with force data to estimate a dense deformation field, through a lightweight physics-aware module inspired by Hooke's law. This design enables PADReg to achieve physically plausible registration with better anatomical alignment than previous methods relying solely on image similarity. Experiments on in-vivo datasets demonstrate that it attains a HD95 of 12.90, which is 21.34\% better than state-of-the-art methods. The source code is available at https://github.com/evelynskip/PADReg.
Authors: Tong Sun, Hongliang Ye, Jilin Mei, Liang Chen, Fangzhou Zhao, Leiqiang Zong, Yu Hu
Abstract: Off-road freespace detection is more challenging than on-road scenarios because of the blurred boundaries of traversable areas. Previous state-of-the-art (SOTA) methods employ multi-modal fusion of RGB images and LiDAR data. However, due to the significant increase in inference time when calculating surface normal maps from LiDAR data, multi-modal methods are not suitable for real-time applications, particularly in real-world scenarios where higher FPS is required compared to slow navigation. This paper presents a novel RGB-only approach for off-road freespace detection, named ROD, eliminating the reliance on LiDAR data and its computational demands. Specifically, we utilize a pre-trained Vision Transformer (ViT) to extract rich features from RGB images. Additionally, we design a lightweight yet efficient decoder, which together improve both precision and inference speed. ROD establishes a new SOTA on ORFD and RELLIS-3D datasets, as well as an inference speed of 50 FPS, significantly outperforming prior models.
Authors: Qi Zheng, Li-Heng Chen, Chenlong He, Neil Berkbeck, Yilin Wang, Balu Adsumilli, Alan C. Bovik, Yibo Fan, Zhengzhong Tu
Abstract: Although there have been notable advancements in video compression technologies in recent years, banding artifacts remain a serious issue affecting the quality of compressed videos, particularly on smooth regions of high-definition videos. Noticeable banding artifacts can severely impact the perceptual quality of videos viewed on a high-end HDTV or high-resolution screen. Hence, there is a pressing need for a systematic investigation of the banding video quality assessment problem for advanced video codecs. Given that the existing publicly available datasets for studying banding artifacts are limited to still picture data only, which cannot account for temporal banding dynamics, we have created a first-of-a-kind open video dataset, dubbed LIVE-YT-Banding, which consists of 160 videos generated by four different compression parameters using the AV1 video codec. A total of 7,200 subjective opinions are collected from a cohort of 45 human subjects. To demonstrate the value of this new resources, we tested and compared a variety of models that detect banding occurrences, and measure their impact on perceived quality. Among these, we introduce an effective and efficient new no-reference (NR) video quality evaluator which we call CBAND. CBAND leverages the properties of the learned statistics of natural images expressed in the embeddings of deep neural networks. Our experimental results show that the perceptual banding prediction performance of CBAND significantly exceeds that of previous state-of-the-art models, and is also orders of magnitude faster. Moreover, CBAND can be employed as a differentiable loss function to optimize video debanding models. The LIVE-YT-Banding database, code, and pre-trained model are all publically available at https://github.com/uniqzheng/CBAND.
Authors: Ouyang Xu, Baoming Zhang, Ruiyu Mao, Yunhui Guo
Abstract: Deep learning models for visual recognition often exhibit systematic errors due to underrepresented semantic subpopulations. Although existing debugging frameworks can pinpoint these failures by identifying key failure attributes, repairing the model effectively remains difficult. Current solutions often rely on manually designed prompts to generate synthetic training images -- an approach prone to distribution shift and semantic errors. To overcome these challenges, we introduce a model repair module that builds on an interpretable failure attribution pipeline. Our approach uses a conditional text-to-image model to generate semantically faithful and targeted images for failure cases. To preserve the quality and relevance of the generated samples, we further employ a large vision-language model (LVLM) to filter the outputs, enforcing alignment with the original data distribution and maintaining semantic consistency. By retraining vision models with this rare-case-augmented synthetic dataset, we significantly reduce errors associated with rare cases. Our experiments demonstrate that this targeted repair strategy improves model robustness without introducing new bugs. Code is available at https://github.com/oxu2/SafeFix
Authors: Zunjie Xiao, Xiao Wu, Tianhang Liu, Lingxi Hu, Yinling Zhang, Xiaoqing Zhang, Risa Higashita, Jiang Liu
Abstract: Precise lens structure segmentation is essential for the design of intraocular lenses (IOLs) in cataract surgery. Existing deep segmentation networks typically weight all pixels equally under cross-entropy (CE) loss, overlooking the fact that sub-regions of lens structures are inhomogeneous (e.g., some regions perform better than others) and that boundary regions often suffer from poor segmentation calibration at the pixel level. Clinically, experts annotate different sub-regions of lens structures with varying confidence levels, considering factors such as sub-region proportions, ambiguous boundaries, and lens structure shapes. Motivated by this observation, we propose an Adaptive Confidence-Wise (ACW) loss to group each lens structure sub-region into different confidence sub-regions via a confidence threshold from the unique region aspect, aiming to exploit the potential of expert annotation confidence prior. Specifically, ACW clusters each target region into low-confidence and high-confidence groups and then applies a region-weighted loss to reweigh each confidence group. Moreover, we design an adaptive confidence threshold optimization algorithm to adjust the confidence threshold of ACW dynamically. Additionally, to better quantify the miscalibration errors in boundary region segmentation, we propose a new metric, termed Boundary Expected Calibration Error (BECE). Extensive experiments on a clinical lens structure AS-OCT dataset and other multi-structure datasets demonstrate that our ACW significantly outperforms competitive segmentation loss methods across different deep segmentation networks (e.g., MedSAM). Notably, our method surpasses CE with 6.13% IoU gain, 4.33% DSC increase, and 4.79% BECE reduction in lens structure segmentation under U-Net. The code of this paper is available at https://github.com/XiaoLing12138/Adaptive-Confidence-Wise-Loss.
URLs: https://github.com/XiaoLing12138/Adaptive-Confidence-Wise-Loss.
Authors: Andrea Montibeller, Dasara Shullani, Daniele Baracchi, Alessandro Piva, Giulia Boato
Abstract: The growing presence of AI-generated videos on social networks poses new challenges for deepfake detection, as detectors trained under controlled conditions often fail to generalize to real-world scenarios. A key factor behind this gap is the aggressive, proprietary compression applied by platforms like YouTube and Facebook, which launder low-level forensic cues. However, replicating these transformations at scale is difficult due to API limitations and data-sharing constraints. For these reasons, we propose a first framework that emulates the video sharing pipelines of social networks by estimating compression and resizing parameters from a small set of uploaded videos. These parameters enable a local emulator capable of reproducing platform-specific artifacts on large datasets without direct API access. Experiments on FaceForensics++ videos shared via social networks demonstrate that our emulated data closely matches the degradation patterns of real uploads. Furthermore, detectors fine-tuned on emulated videos achieve comparable performance to those trained on actual shared media. Our approach offers a scalable and practical solution for bridging the gap between lab-based training and real-world deployment of deepfake detectors, particularly in the underexplored domain of compressed video content.
Authors: Trong-Thuan Nguyen, Viet-Tham Huynh, Quang-Thuc Nguyen, Hoang-Phuc Nguyen, Long Le Bao, Thai Hoang Minh, Minh Nguyen Anh, Thang Nguyen Tien, Phat Nguyen Thuan, Huy Nguyen Phong, Bao Huynh Thai, Vinh-Tiep Nguyen, Duc-Vu Nguyen, Phu-Hoa Pham, Minh-Huy Le-Hoang, Nguyen-Khang Le, Minh-Chinh Nguyen, Minh-Quan Ho, Ngoc-Long Tran, Hien-Long Le-Hoang, Man-Khoi Tran, Anh-Duong Tran, Kim Nguyen, Quan Nguyen Hung, Dat Phan Thanh, Hoang Tran Van, Tien Huynh Viet, Nhan Nguyen Viet Thien, Dinh-Khoi Vo, Van-Loc Nguyen, Trung-Nghia Le, Tam V. Nguyen, Minh-Triet Tran
Abstract: Recent 3D retrieval systems are typically designed for simple, controlled scenarios, such as identifying an object from a cropped image or a brief description. However, real-world scenarios are more complex, often requiring the recognition of an object in a cluttered scene based on a vague, free-form description. To this end, we present ROOMELSA, a new benchmark designed to evaluate a system's ability to interpret natural language. Specifically, ROOMELSA attends to a specific region within a panoramic room image and accurately retrieves the corresponding 3D model from a large database. In addition, ROOMELSA includes over 1,600 apartment scenes, nearly 5,200 rooms, and more than 44,000 targeted queries. Empirically, while coarse object retrieval is largely solved, only one top-performing model consistently ranked the correct match first across nearly all test cases. Notably, a lightweight CLIP-based model also performed well, although it struggled with subtle variations in materials, part structures, and contextual cues, resulting in occasional errors. These findings highlight the importance of tightly integrating visual and language understanding. By bridging the gap between scene-level grounding and fine-grained 3D retrieval, ROOMELSA establishes a new benchmark for advancing robust, real-world 3D recognition systems.
Authors: Tianyu Xiong, Dayi Tan, Wei Tian
Abstract: Animal pose estimation is a fundamental task in computer vision, with growing importance in ecological monitoring, behavioral analysis, and intelligent livestock management. Compared to human pose estimation, animal pose estimation is more challenging due to high interspecies morphological diversity, complex body structures, and limited annotated data. In this work, we introduce DiffPose-Animal, a novel diffusion-based framework for top-down animal pose estimation. Unlike traditional heatmap regression methods, DiffPose-Animal reformulates pose estimation as a denoising process under the generative framework of diffusion models. To enhance semantic guidance during keypoint generation, we leverage large language models (LLMs) to extract both global anatomical priors and local keypoint-wise semantics based on species-specific prompts. These textual priors are encoded and fused with image features via cross-attention modules to provide biologically meaningful constraints throughout the denoising process. Additionally, a diffusion-based keypoint decoder is designed to progressively refine pose predictions, improving robustness to occlusion and annotation sparsity. Extensive experiments on public animal pose datasets demonstrate the effectiveness and generalization capability of our method, especially under challenging scenarios with diverse species, cluttered backgrounds, and incomplete keypoints.
Authors: Yingxue Pang, Shijie Zhao, Mengxi Guo, Junlin Li, Li Zhang
Abstract: Sharpening is a widely adopted video enhancement technique. However, uniform sharpening intensity ignores texture variations, degrading video quality. Sharpening also increases bitrate, and there's a lack of techniques to optimally allocate these additional bits across diverse regions. Thus, this paper proposes RPO-AdaSharp, an end-to-end region-adaptive video sharpening model for both perceptual enhancement and bitrate savings. We use the coding tree unit (CTU) partition mask as prior information to guide and constrain the allocation of increased bits. Experiments on benchmarks demonstrate the effectiveness of the proposed model qualitatively and quantitatively.
Authors: Yao Lu, Jiawei Li, Ming Jiang
Abstract: In recent years, Neural Radiance Fields (NeRF) have achieved remarkable progress in dynamic human reconstruction and rendering. Part-based rendering paradigms, guided by human segmentation, allow for flexible parameter allocation based on structural complexity, thereby enhancing representational efficiency. However, existing methods still struggle with complex pose variations, often producing unnatural transitions at part boundaries and failing to reconstruct occluded regions accurately in monocular settings. We propose MonoPartNeRF, a novel framework for monocular dynamic human rendering that ensures smooth transitions and robust occlusion recovery. First, we build a bidirectional deformation model that combines rigid and non-rigid transformations to establish a continuous, reversible mapping between observation and canonical spaces. Sampling points are projected into a parameterized surface-time space (u, v, t) to better capture non-rigid motion. A consistency loss further suppresses deformation-induced artifacts and discontinuities. We introduce a part-based pose embedding mechanism that decomposes global pose vectors into local joint embeddings based on body regions. This is combined with keyframe pose retrieval and interpolation, along three orthogonal directions, to guide pose-aware feature sampling. A learnable appearance code is integrated via attention to model dynamic texture changes effectively. Experiments on the ZJU-MoCap and MonoCap datasets demonstrate that our method significantly outperforms prior approaches under complex pose and occlusion conditions, achieving superior joint alignment, texture fidelity, and structural continuity.
Authors: Luis S. Luevano, Pavel Korshunov, Sebastien Marcel
Abstract: Face aging or de-aging with generative AI has gained significant attention for its applications in such fields like forensics, security, and media. However, most state of the art methods rely on conditional Generative Adversarial Networks (GANs), Diffusion-based models, or Visual Language Models (VLMs) to age or de-age faces based on predefined age categories and conditioning via loss functions, fine-tuning, or text prompts. The reliance on such conditioning leads to complex training requirements, increased data needs, and challenges in generating consistent results. Additionally, identity preservation is rarely taken into accountor evaluated on a single face recognition system without any control or guarantees on whether identity would be preserved in a generated aged/de-aged face. In this paper, we propose to synthesize aged and de-aged faces via editing latent space of StyleGAN2 using a simple support vector modeling of aging/de-aging direction and several feature selection approaches. By using two state-of-the-art face recognition systems, we empirically find the identity preserving subspace within the StyleGAN2 latent space, so that an apparent age of a given face can changed while preserving the identity. We then propose a simple yet practical formula for estimating the limits on aging/de-aging parameters that ensures identity preservation for a given input face. Using our method and estimated parameters we have generated a public dataset of synthetic faces at different ages that can be used for benchmarking cross-age face recognition, age assurance systems, or systems for detection of synthetic images. Our code and dataset are available at the project page https://www.idiap.ch/paper/agesynth/
Authors: Shi-Chen Zhang, Yunheng Li, Yu-Huan Wu, Qibin Hou, Ming-Ming Cheng
Abstract: Semantic segmentation is fundamental to vision systems requiring pixel-level scene understanding, yet deploying it on resource-constrained devices demands efficient architectures. Although existing methods achieve real-time inference through lightweight designs, we reveal their inherent limitation: misalignment between class representations and image features caused by a per-pixel classification paradigm. With experimental analysis, we find that this paradigm results in a highly challenging assumption for efficient scenarios: Image pixel features should not vary for the same category in different images. To address this dilemma, we propose a coupled dual-branch offset learning paradigm that explicitly learns feature and class offsets to dynamically refine both class representations and spatial image features. Based on the proposed paradigm, we construct an efficient semantic segmentation network, OffSeg. Notably, the offset learning paradigm can be adopted to existing methods with no additional architectural changes. Extensive experiments on four datasets, including ADE20K, Cityscapes, COCO-Stuff-164K, and Pascal Context, demonstrate consistent improvements with negligible parameters. For instance, on the ADE20K dataset, our proposed offset learning paradigm improves SegFormer-B0, SegNeXt-T, and Mask2Former-Tiny by 2.7%, 1.9%, and 2.6% mIoU, respectively, with only 0.1-0.2M additional parameters required.
Authors: Yuqi Peng, Lingtao Zheng, Yufeng Yang, Yi Huang, Mingfu Yan, Jianzhuang Liu, Shifeng Chen
Abstract: Personalized text-to-image generation aims to synthesize novel images of a specific subject or style using only a few reference images. Recent methods based on Low-Rank Adaptation (LoRA) enable efficient single-concept customization by injecting lightweight, concept-specific adapters into pre-trained diffusion models. However, combining multiple LoRA modules for multi-concept generation often leads to identity missing and visual feature leakage. In this work, we identify two key issues behind these failures: (1) token-wise interference among different LoRA modules, and (2) spatial misalignment between the attention map of a rare token and its corresponding concept-specific region. To address these issues, we propose Token-Aware LoRA (TARA), which introduces a token mask to explicitly constrain each module to focus on its associated rare token to avoid interference, and a training objective that encourages the spatial attention of a rare token to align with its concept region. Our method enables training-free multi-concept composition by directly injecting multiple independently trained TARA modules at inference time. Experimental results demonstrate that TARA enables efficient multi-concept inference and effectively preserving the visual identity of each concept by avoiding mutual interference between LoRA modules. The code and models are available at https://github.com/YuqiPeng77/TARA.
Authors: Noor Ahmed, Cameron Braunstein, Steffen Eger, Eddy Ilg
Abstract: Recent Multi-Modal Large Language Models (MLLMs) have demonstrated strong capabilities in learning joint representations from text and images. However, their spatial reasoning remains limited. We introduce 3DFroMLLM, a novel framework that enables the generation of 3D object prototypes directly from MLLMs, including geometry and part labels. Our pipeline is agentic, comprising a designer, coder, and visual inspector operating in a refinement loop. Notably, our approach requires no additional training data or detailed user instructions. Building on prior work in 2D generation, we demonstrate that rendered images produced by our framework can be effectively used for image classification pretraining tasks and outperforms previous methods by 15%. As a compelling real-world use case, we show that the generated prototypes can be leveraged to improve fine-grained vision-language models by using the rendered, part-labeled prototypes to fine-tune CLIP for part segmentation and achieving a 55% accuracy improvement without relying on any additional human-labeled data.
Authors: Diego Frias
Abstract: This work presents a novel framework for No-Reference Image Quality Assessment (NR-IQA) founded on the analysis of directional image curvature. Within this framework, we define a measure of Anisotropic Texture Richness (ATR), which is computed at the pixel level using two tunable thresholds -- one permissive and one restrictive -- that quantify orthogonal texture suppression. When its parameters are optimized for a specific artifact, the resulting ATR score serves as a high-performance quality metric, achieving Spearman correlations with human perception of approximately -0.93 for Gaussian blur and -0.95 for white noise on the LIVE dataset. The primary contribution is a two-stage system that leverages the differential response of ATR to various distortions. First, the system utilizes the signature from two specialist ATR configurations to classify the primary artifact type (blur vs. noise) with over 97% accuracy. Second, following classification, it employs a dedicated regression model mapping the relevant ATR score to a quality rating to quantify the degradation. On a combined dataset, the complete system predicts human scores with a coefficient of determination (R2) of 0.892 and a Root Mean Square Error (RMSE) of 5.17 DMOS points. This error corresponds to just 7.4% of the dataset's total quality range, demonstrating high predictive accuracy. This establishes our framework as a robust, dual-purpose tool for the classification and subsequent quantification of image degradation.
Authors: Yingxue Pang, Shijie Zhao, Junlin Li, Li Zhang
Abstract: High-frequency components are crucial for maintaining video clarity and realism, but they also significantly impact coding bitrate, resulting in increased bandwidth and storage costs. This paper presents an end-to-end learning-based framework for adaptive high-frequency preprocessing to enhance subjective quality and save bitrate in video coding. The framework employs the Frequency-attentive Feature pyramid Prediction Network (FFPN) to predict the optimal high-frequency preprocessing strategy, guiding subsequent filtering operators to achieve the optimal tradeoff between bitrate and quality after compression. For training FFPN, we pseudo-label each training video with the optimal strategy, determined by comparing the rate-distortion (RD) performance across different preprocessing types and strengths. Distortion is measured using the latest quality assessment metric. Comprehensive evaluations on multiple datasets demonstrate the visually appealing enhancement capabilities and bitrate savings achieved by our framework.
Authors: Lin Zeng, Boming Zhao, Jiarui Hu, Xujie Shen, Ziqiang Dang, Hujun Bao, Zhaopeng Cui
Abstract: Novel view synthesis with neural models has advanced rapidly in recent years, yet adapting these models to scene changes remains an open problem. Existing methods are either labor-intensive, requiring extensive model retraining, or fail to capture detailed types of changes over time. In this paper, we present GaussianUpdate, a novel approach that combines 3D Gaussian representation with continual learning to address these challenges. Our method effectively updates the Gaussian radiance fields with current data while preserving information from past scenes. Unlike existing methods, GaussianUpdate explicitly models different types of changes through a novel multi-stage update strategy. Additionally, we introduce a visibility-aware continual learning approach with generative replay, enabling self-aware updating without the need to store images. The experiments on the benchmark dataset demonstrate our method achieves superior and real-time rendering with the capability of visualizing changes over different times
Authors: Chaoyi Wang, Yifan Yang, Jun Pei, Lijie Xia, Jianpo Liu, Xiaobing Yuan, Xinhan Di
Abstract: Creating realistic, fully animatable whole-body avatars from a single portrait is challenging due to limitations in capturing subtle expressions, body movements, and dynamic backgrounds. Current evaluation datasets and metrics fall short in addressing these complexities. To bridge this gap, we introduce the Whole-Body Benchmark Dataset (WB-DH), an open-source, multi-modal benchmark designed for evaluating whole-body animatable avatar generation. Key features include: (1) detailed multi-modal annotations for fine-grained guidance, (2) a versatile evaluation framework, and (3) public access to the dataset and tools at https://github.com/deepreasonings/WholeBodyBenchmark.
Authors: Noor Islam S. Mohammad
Abstract: Robust depth estimation in light field imaging remains a critical challenge for pattern recognition applications such as augmented reality, biomedical imaging, and scene reconstruction. While existing approaches often rely heavily on deep convolutional neural networks, they tend to incur high computational costs and struggle in noisy real-world environments. This paper proposes a novel lightweight depth estimation pipeline that integrates light field-based disparity information with a directed random walk refinement algorithm. Unlike traditional CNN-based methods, our approach enhances depth map consistency without requiring extensive training or large-scale datasets. The proposed method was evaluated on the 4D Light Field Benchmark dataset and a diverse set of real-world images. Experimental results indicate that while performance slightly declines under uncontrolled conditions, the algorithm consistently maintains low computational complexity and competitive accuracy compared to state-of-the-art deep learning models. These findings highlight the potential of our method as a robust and efficient alternative for depth estimation and segmentation in light field imaging. The work provides insights into practical algorithm design for light field-based pattern recognition and opens new directions for integrating probabilistic graph models with depth sensing frameworks.
Authors: Bin Ren, Xiaoshui Huang, Mengyuan Liu, Hong Liu, Fabio Poiesi, Nicu Sebe, Guofeng Mei
Abstract: Vision transformers (ViTs) have recently been widely applied to 3D point cloud understanding, with masked autoencoding as the predominant pre-training paradigm. However, the challenge of learning dense and informative semantic features from point clouds via standard ViTs remains underexplored. We propose MaskClu, a novel unsupervised pre-training method for ViTs on 3D point clouds that integrates masked point modeling with clustering-based learning. MaskClu is designed to reconstruct both cluster assignments and cluster centers from masked point clouds, thus encouraging the model to capture dense semantic information. Additionally, we introduce a global contrastive learning mechanism that enhances instance-level feature learning by contrasting different masked views of the same point cloud. By jointly optimizing these complementary objectives, i.e., dense semantic reconstruction, and instance-level contrastive learning. MaskClu enables ViTs to learn richer and more semantically meaningful representations from 3D point clouds. We validate the effectiveness of our method via multiple 3D tasks, including part segmentation, semantic segmentation, object detection, and classification, where MaskClu sets new competitive results. The code and models will be released at:https://github.com/Amazingren/maskclu.
Authors: David Bouget, Mathilde Gajda Faanes, Asgeir Store Jakola, Frederik Barkhof, Hilko Ardon, Lorenzo Bello, Mitchel S. Berger, Shawn L. Hervey-Jumper, Julia Furtner, Albert J. S. Idema, Barbara Kiesel, Georg Widhalm, Rishi Nandoe Tewarie, Emmanuel Mandonnet, Pierre A. Robe, Michiel Wagemakers, Timothy R. Smith, Philip C. De Witt Hamer, Ole solheim, Ingerid Reinertsen
Abstract: Magnetic resonance (MR) imaging is essential for evaluating central nervous system (CNS) tumors, guiding surgical planning, treatment decisions, and assessing postoperative outcomes and complication risks. While recent work has advanced automated tumor segmentation and report generation, most efforts have focused on preoperative data, with limited attention to postoperative imaging analysis. This study introduces a comprehensive pipeline for standardized postsurtical reporting in CNS tumors. Using the Attention U-Net architecture, segmentation models were trained for the preoperative (non-enhancing) tumor core, postoperative contrast-enhancing residual tumor, and resection cavity. Additionally, MR sequence classification and tumor type identification for contrast-enhancing lesions were explored using the DenseNet architecture. The models were integrated into a reporting pipeline, following the RANO 2.0 guidelines. Training was conducted on multicentric datasets comprising 2000 to 7000 patients, using a 5-fold cross-validation. Evaluation included patient-, voxel-, and object-wise metrics, with benchmarking against the latest BraTS challenge results. The segmentation models achieved average voxel-wise Dice scores of 87%, 66%, 70%, and 77% for the tumor core, non-enhancing tumor core, contrast-enhancing residual tumor, and resection cavity, respectively. Classification models reached 99.5% balanced accuracy in MR sequence classification and 80% in tumor type classification. The pipeline presented in this study enables robust, automated segmentation, MR sequence classification, and standardized report generation aligned with RANO 2.0 guidelines, enhancing postoperative evaluation and clinical decision-making. The proposed models and methods were integrated into Raidionics, open-source software platform for CNS tumor analysis, now including a dedicated module for postsurgical analysis.
Authors: Jintao Cheng, Jiehao Luo, Xieyuanli Chen, Jin Wu, Rui Fan, Xiaoyu Tang, Wei Zhang
Abstract: LiDAR-based Place Recognition (LPR) remains a critical task in Embodied Artificial Intelligence (AI) and Autonomous Driving, primarily addressing localization challenges in GPS-denied environments and supporting loop closure detection. Existing approaches reduce place recognition to a Euclidean distance-based metric learning task, neglecting the feature space's intrinsic structures and intra-class variances. Such Euclidean-centric formulation inherently limits the model's capacity to capture nonlinear data distributions, leading to suboptimal performance in complex environments and temporal-varying scenarios. To address these challenges, we propose a novel cross-view network based on an innovative fusion paradigm. Our framework introduces a pseudo-global information guidance mechanism that coordinates multi-modal branches to perform feature learning within a unified semantic space. Concurrently, we propose a Manifold Adaptation and Pairwise Variance-Locality Learning Metric that constructs a Symmetric Positive Definite (SPD) matrix to compute Mahalanobis distance, superseding traditional Euclidean distance metrics. This geometric formulation enables the model to accurately characterize intrinsic data distributions and capture complex inter-class dependencies within the feature space. Experimental results demonstrate that the proposed algorithm achieves competitive performance, particularly excelling in complex environmental conditions.
Authors: Miruna-Alexandra Gafencu, Reem Shaban, Yordanka Velikova, Mohammad Farid Azampour, Nassir Navab
Abstract: Ultrasound (US) imaging is increasingly used in spinal procedures due to its real-time, radiation-free capabilities; however, its effectiveness is hindered by shadowing artifacts that obscure deeper tissue structures. Traditional approaches, such as CT-to-US registration, incorporate anatomical information from preoperative CT scans to guide interventions, but they are limited by complex registration requirements, differences in spine curvature, and the need for recent CT imaging. Recent shape completion methods can offer an alternative by reconstructing spinal structures in US data, while being pretrained on large set of publicly available CT scans. However, these approaches are typically offline and have limited reproducibility. In this work, we introduce a novel integrated system that combines robotic ultrasound with real-time shape completion to enhance spinal visualization. Our robotic platform autonomously acquires US sweeps of the lumbar spine, extracts vertebral surfaces from ultrasound, and reconstructs the complete anatomy using a deep learning-based shape completion network. This framework provides interactive, real-time visualization with the capability to autonomously repeat scans and can enable navigation to target locations. This can contribute to better consistency, reproducibility, and understanding of the underlying anatomy. We validate our approach through quantitative experiments assessing shape completion accuracy and evaluations of multiple spine acquisition protocols on a phantom setup. Additionally, we present qualitative results of the visualization on a volunteer scan.
Authors: Leona \v{Z}\r{u}rkov\'a (IT4Innovations, VSB - Technical University of Ostrava), Petr Strako\v{s} (IT4Innovations, VSB - Technical University of Ostrava), Michal Krav\v{c}enko (IT4Innovations, VSB - Technical University of Ostrava), Tom\'a\v{s} Brzobohat\'y (IT4Innovations, VSB - Technical University of Ostrava), Lubom\'ir \v{R}\'iha (IT4Innovations, VSB - Technical University of Ostrava)
Abstract: Volumetric data compression is critical in fields like medical imaging, scientific simulation, and entertainment. We introduce a structure-free neural compression method combining Fourierfeature encoding with selective voxel sampling, yielding compact volumetric representations and faster convergence. Our dynamic voxel selection uses morphological dilation to prioritize active regions, reducing redundant computation without any hierarchical metadata. In the experiment, sparse training reduced training time by 63.7 % (from 30 to 11 minutes) with only minor quality loss: PSNR dropped 0.59 dB (from 32.60 to 32.01) and SSIM by 0.008 (from 0.948 to 0.940). The resulting neural representation, stored solely as network weights, achieves a compression rate of 14 and eliminates traditional data-loading overhead. This connects coordinate-based neural representation with efficient volumetric compression, offering a scalable, structure-free solution for practical applications.
Authors: Eduarda Caldeira, Fadi Boutros, Naser Damer
Abstract: Face Morphing Attack Detection (MAD) is a critical challenge in face recognition security, where attackers can fool systems by interpolating the identity information of two or more individuals into a single face image, resulting in samples that can be verified as belonging to multiple identities by face recognition systems. While multimodal foundation models (FMs) like CLIP offer strong zero-shot capabilities by jointly modeling images and text, most prior works on FMs for biometric recognition have relied on fine-tuning for specific downstream tasks, neglecting their potential for direct, generalizable deployment. This work explores a pure zero-shot approach to MAD by leveraging CLIP without any additional training or fine-tuning, focusing instead on the design and aggregation of multiple textual prompts per class. By aggregating the embeddings of diverse prompts, we better align the model's internal representations with the MAD task, capturing richer and more varied cues indicative of bona-fide or attack samples. Our results show that prompt aggregation substantially improves zero-shot detection performance, demonstrating the effectiveness of exploiting foundation models' built-in multimodal knowledge through efficient prompt engineering.
Authors: Wenhan Wu, Zhishuai Guo, Chen Chen, Aidong Lu
Abstract: Skeleton-based action recognition (SAR) has achieved impressive progress with transformer architectures. However, existing methods often rely on complex module compositions and heavy designs, leading to increased parameter counts, high computational costs, and limited scalability. In this paper, we propose a unified spatio-temporal lightweight transformer framework that integrates spatial and temporal modeling within a single attention module, eliminating the need for separate temporal modeling blocks. This approach reduces redundant computations while preserving temporal awareness within the spatial modeling process. Furthermore, we introduce a simplified multi-scale pooling fusion module that combines local and global pooling pathways to enhance the model's ability to capture fine-grained local movements and overarching global motion patterns. Extensive experiments on benchmark datasets demonstrate that our lightweight model achieves a superior balance between accuracy and efficiency, reducing parameter complexity by over 58% and lowering computational cost by over 60% compared to state-of-the-art transformer-based baselines, while maintaining competitive recognition performance.
Authors: Ao Ma, Jiasong Feng, Ke Cao, Jing Wang, Yun Wang, Quanwei Zhang, Zhanjie Zhang
Abstract: Storytelling tasks involving generating consistent subjects have gained significant attention recently. However, existing methods, whether training-free or training-based, continue to face challenges in maintaining subject consistency due to the lack of fine-grained guidance and inter-frame interaction. Additionally, the scarcity of high-quality data in this field makes it difficult to precisely control storytelling tasks, including the subject's position, appearance, clothing, expression, and posture, thereby hindering further advancements. In this paper, we demonstrate that layout conditions, such as the subject's position and detailed attributes, effectively facilitate fine-grained interactions between frames. This not only strengthens the consistency of the generated frame sequence but also allows for precise control over the subject's position, appearance, and other key details. Building on this, we introduce an advanced storytelling task: Layout-Togglable Storytelling, which enables precise subject control by incorporating layout conditions. To address the lack of high-quality datasets with layout annotations for this task, we develop Lay2Story-1M, which contains over 1 million 720p and higher-resolution images, processed from approximately 11,300 hours of cartoon videos. Building on Lay2Story-1M, we create Lay2Story-Bench, a benchmark with 3,000 prompts designed to evaluate the performance of different methods on this task. Furthermore, we propose Lay2Story, a robust framework based on the Diffusion Transformers (DiTs) architecture for Layout-Togglable Storytelling tasks. Through both qualitative and quantitative experiments, we find that our method outperforms the previous state-of-the-art (SOTA) techniques, achieving the best results in terms of consistency, semantic correlation, and aesthetic quality.
Authors: Elman Ghazaei, Erchan Aptoula
Abstract: The Earth's surface is constantly changing, and detecting these changes provides valuable insights that benefit various aspects of human society. While traditional change detection methods have been employed to detect changes from bi-temporal images, these approaches typically require expert knowledge for accurate interpretation. To enable broader and more flexible access to change information by non-expert users, the task of Change Detection Visual Question Answering (CDVQA) has been introduced. However, existing CDVQA methods have been developed under the assumption that training and testing datasets share similar distributions. This assumption does not hold in real-world applications, where domain shifts often occur. In this paper, the CDVQA task is revisited with a focus on addressing domain shift. To this end, a new multi-modal and multi-domain dataset, BrightVQA, is introduced to facilitate domain generalization research in CDVQA. Furthermore, a novel state space model, termed Text-Conditioned State Space Model (TCSSM), is proposed. The TCSSM framework is designed to leverage both bi-temporal imagery and geo-disaster-related textual information in an unified manner to extract domain-invariant features across domains. Input-dependent parameters existing in TCSSM are dynamically predicted by using both bi-temporal images and geo-disaster-related description, thereby facilitating the alignment between bi-temporal visual data and the associated textual descriptions. Extensive experiments are conducted to evaluate the proposed method against state-of-the-art models, and superior performance is consistently demonstrated. The code and dataset will be made publicly available upon acceptance at https://github.com/Elman295/TCSSM.
Authors: Zhentao Fan, Zongzuo Wang, Weiwei Zhang
Abstract: Existing cache-based acceleration methods for video diffusion models primarily skip early or mid denoising steps, which often leads to structural discrepancies relative to full-timestep generation and can hinder instruction following and character consistency. We present TaoCache, a training-free, plug-and-play caching strategy that, instead of residual-based caching, adopts a fixed-point perspective to predict the model's noise output and is specifically effective in late denoising stages. By calibrating cosine similarities and norm ratios of consecutive noise deltas, TaoCache preserves high-resolution structure while enabling aggressive skipping. The approach is orthogonal to complementary accelerations such as Pyramid Attention Broadcast (PAB) and TeaCache, and it integrates seamlessly into DiT-based frameworks. Across Latte-1, OpenSora-Plan v110, and Wan2.1, TaoCache attains substantially higher visual quality (LPIPS, SSIM, PSNR) than prior caching methods under the same speedups.
Authors: Ding Xia, Naoto Inoue, Qianru Qiu, Kotaro Kikuchi
Abstract: Colors play a crucial role in the design of vector graphic documents by enhancing visual appeal, facilitating communication, improving usability, and ensuring accessibility. In this context, color recommendation involves suggesting appropriate colors to complete or refine a design when one or more colors are missing or require alteration. Traditional methods often struggled with these challenges due to the complex nature of color design and the limited data availability. In this study, we explored the use of pretrained Large Language Models (LLMs) and their commonsense reasoning capabilities for color recommendation, raising the question: Can pretrained LLMs serve as superior designers for color recommendation tasks? To investigate this, we developed a robust, rigorously validated pipeline, ColorGPT, that was built by systematically testing multiple color representations and applying effective prompt engineering techniques. Our approach primarily targeted color palette completion by recommending colors based on a set of given colors and accompanying context. Moreover, our method can be extended to full palette generation, producing an entire color palette corresponding to a provided textual description. Experimental results demonstrated that our LLM-based pipeline outperformed existing methods in terms of color suggestion accuracy and the distribution of colors in the color palette completion task. For the full palette generation task, our approach also yielded improvements in color diversity and similarity compared to current techniques.
Authors: Ming Nie, Chunwei Wang, Hang Xu, Li Zhang
Abstract: Recently, with the emergence of large language models, multimodal LLMs have demonstrated exceptional capabilities in image and video modalities. Despite advancements in video comprehension, the substantial computational demands of long video sequences lead current video LLMs (Vid-LLMs) to employ compression strategies at both the inter-frame level (e.g., uniform sampling of video frames) and intra-frame level (e.g., condensing all visual tokens of each frame into a limited number). However, this approach often neglects the uneven temporal distribution of critical information across frames, risking the omission of keyframes that contain essential temporal and semantic details. To tackle these challenges, we propose KFFocus, a method designed to efficiently compress video tokens and emphasize the informative context present within video frames. We substitute uniform sampling with a refined approach inspired by classic video compression principles to identify and capture keyframes based on their temporal redundancy. By assigning varying condensation ratios to frames based on their contextual relevance, KFFocus efficiently reduces token redundancy while preserving informative content details. Additionally, we introduce a spatiotemporal modeling module that encodes both the temporal relationships between video frames and the spatial structure within each frame, thus providing Vid-LLMs with a nuanced understanding of spatial-temporal dynamics. Extensive experiments on widely recognized video understanding benchmarks, especially long video scenarios, demonstrate that KFFocus significantly outperforms existing methods, achieving substantial computational efficiency and enhanced accuracy.
Authors: Zan Wang, Jingze Zhang, Yixin Chen, Baoxiong Jia, Wei Liang, Siyuan Huang
Abstract: Despite significant advancements in human motion generation, current motion representations, typically formulated as discrete frame sequences, still face two critical limitations: (i) they fail to capture motion from a multi-scale perspective, limiting the capability in complex patterns modeling; (ii) they lack compositional flexibility, which is crucial for model's generalization in diverse generation tasks. To address these challenges, we introduce MSQ, a novel quantization method that compresses the motion sequence into multi-scale discrete tokens across spatial and temporal dimensions. MSQ employs distinct encoders to capture body parts at varying spatial granularities and temporally interpolates the encoded features into multiple scales before quantizing them into discrete tokens. Building on this representation, we establish a generative mask modeling model to effectively support motion editing, motion control, and conditional motion generation. Through quantitative and qualitative analysis, we show that our quantization method enables the seamless composition of motion tokens without requiring specialized design or re-training. Furthermore, extensive evaluations demonstrate that our approach outperforms existing baseline methods on various benchmarks.
Authors: Yuhao Wang, Wei Xi
Abstract: Convolutional neural networks (ConvNets) with large effective receptive field (ERF), still in their early stages, have demonstrated promising effectiveness while constrained by high parameters and FLOPs costs and disrupted asymptotically Gaussian distribution (AGD) of ERF. This paper proposes an alternative paradigm: rather than merely employing extremely large ERF, it is more effective and efficient to expand the ERF while maintaining AGD of ERF by proper combination of smaller kernels, such as $7\times{7}$, $9\times{9}$, $11\times{11}$. This paper introduces a Three-layer Receptive Field Aggregator and designs a Layer Operator as the fundamental operator from the perspective of receptive field. The ERF can be expanded to the level of existing large-kernel ConvNets through the stack of proposed modules while maintaining AGD of ERF. Using these designs, we propose a universal model for ConvNet of any scale, termed UniConvNet. Extensive experiments on ImageNet-1K, COCO2017, and ADE20K demonstrate that UniConvNet outperforms state-of-the-art CNNs and ViTs across various vision recognition tasks for both lightweight and large-scale models with comparable throughput. Surprisingly, UniConvNet-T achieves $84.2\%$ ImageNet top-1 accuracy with $30M$ parameters and $5.1G$ FLOPs. UniConvNet-XL also shows competitive scalability to big data and large models, acquiring $88.4\%$ top-1 accuracy on ImageNet. Code and models are publicly available at https://github.com/ai-paperwithcode/UniConvNet.
Authors: Luyang Cao, Han Xu, Jian Zhang, Lei Qi, Jiayi Ma, Yinghuan Shi, Yang Gao
Abstract: In low-light image enhancement, Retinex-based deep learning methods have garnered significant attention due to their exceptional interpretability. These methods decompose images into mutually independent illumination and reflectance components, allows each component to be enhanced separately. In fact, achieving perfect decomposition of illumination and reflectance components proves to be quite challenging, with some residuals still existing after decomposition. In this paper, we formally name these residuals as inter-component residuals (ICR), which has been largely underestimated by previous methods. In our investigation, ICR not only affects the accuracy of the decomposition but also causes enhanced components to deviate from the ideal outcome, ultimately reducing the final synthesized image quality. To address this issue, we propose a novel Inter-correction Retinex model (IRetinex) to alleviate ICR during the decomposition and enhancement stage. In the decomposition stage, we leverage inter-component residual reduction module to reduce the feature similarity between illumination and reflectance components. In the enhancement stage, we utilize the feature similarity between the two components to detect and mitigate the impact of ICR within each enhancement unit. Extensive experiments on three low-light benchmark datasets demonstrated that by reducing ICR, our method outperforms state-of-the-art approaches both qualitatively and quantitatively.
Authors: Kaiwen Huang, Tao Zhou, Huazhu Fu, Yizhe Zhang, Yi Zhou, Xiao-Jun Wu
Abstract: Semi-supervised learning has gained considerable popularity in medical image segmentation tasks due to its capability to reduce reliance on expert-examined annotations. Several mean-teacher (MT) based semi-supervised methods utilize consistency regularization to effectively leverage valuable information from unlabeled data. However, these methods often heavily rely on the student model and overlook the potential impact of cognitive biases within the model. Furthermore, some methods employ co-training using pseudo-labels derived from different inputs, yet generating high-confidence pseudo-labels from perturbed inputs during training remains a significant challenge. In this paper, we propose an Uncertainty-aware Cross-training framework for semi-supervised medical image Segmentation (UC-Seg). Our UC-Seg framework incorporates two distinct subnets to effectively explore and leverage the correlation between them, thereby mitigating cognitive biases within the model. Specifically, we present a Cross-subnet Consistency Preservation (CCP) strategy to enhance feature representation capability and ensure feature consistency across the two subnets. This strategy enables each subnet to correct its own biases and learn shared semantics from both labeled and unlabeled data. Additionally, we propose an Uncertainty-aware Pseudo-label Generation (UPG) component that leverages segmentation results and corresponding uncertainty maps from both subnets to generate high-confidence pseudo-labels. We extensively evaluate the proposed UC-Seg on various medical image segmentation tasks involving different modality images, such as MRI, CT, ultrasound, colonoscopy, and so on. The results demonstrate that our method achieves superior segmentation accuracy and generalization performance compared to other state-of-the-art semi-supervised methods. Our code will be released at https://github.com/taozh2017/UCSeg.
Authors: Zhiqiang Yang, Renshuai Tao, Xiaolong Zheng, Guodong Yang, Chunjie Zhang
Abstract: Existing deepfake detection methods heavily depend on labeled training data. However, as AI-generated content becomes increasingly realistic, even \textbf{human annotators struggle to distinguish} between deepfakes and authentic images. This makes the labeling process both time-consuming and less reliable. Specifically, there is a growing demand for approaches that can effectively utilize large-scale unlabeled data from online social networks. Unlike typical unsupervised learning tasks, where categories are distinct, AI-generated faces closely mimic real image distributions and share strong similarities, causing performance drop in conventional strategies. In this paper, we introduce the Dual-Path Guidance Network (DPGNet), to tackle two key challenges: (1) bridging the domain gap between faces from different generation models, and (2) utilizing unlabeled image samples. The method features two core modules: text-guided cross-domain alignment, which uses learnable prompts to unify visual and textual embeddings into a domain-invariant feature space, and curriculum-driven pseudo label generation, which dynamically exploit more informative unlabeled samples. To prevent catastrophic forgetting, we also facilitate bridging between domains via cross-domain knowledge distillation. Extensive experiments on \textbf{11 popular datasets}, show that DPGNet outperforms SoTA approaches by \textbf{6.3\%}, highlighting its effectiveness in leveraging unlabeled data to address the annotation challenges posed by the increasing realism of deepfakes.
Authors: Maxim A. Patratskiy, Alexey K. Kovalev, Aleksandr I. Panov
Abstract: Vision-Language-Action models have demonstrated remarkable capabilities in predicting agent movements within virtual environments and real-world scenarios based on visual observations and textual instructions. Although recent research has focused on enhancing spatial and temporal understanding independently, this paper presents a novel approach that integrates both aspects through visual prompting. We introduce a method that projects visual traces of key points from observations onto depth maps, enabling models to capture both spatial and temporal information simultaneously. The experiments in SimplerEnv show that the mean number of tasks successfully solved increased for 4% compared to SpatialVLA and 19% compared to TraceVLA. Furthermore, we show that this enhancement can be achieved with minimal training data, making it particularly valuable for real-world applications where data collection is challenging. The project page is available at https://ampiromax.github.io/ST-VLA.
Authors: Ori Malca, Dvir Samuel, Gal Chechik
Abstract: Visual concept learning, also known as Text-to-image personalization, is the process of teaching new concepts to a pretrained model. This has numerous applications from product placement to entertainment and personalized design. Here we show that many existing methods can be substantially augmented by adding a personalization step that is (1) specific to the prompt and noise seed, and (2) using two loss terms based on the self- and cross- attention, capturing the identity of the personalized concept. Specifically, we leverage PDM features -- previously designed to capture identity -- and show how they can be used to improve personalized semantic similarity. We evaluate the benefit that our method gains on top of six different personalization methods, and several base text-to-image models (both UNet- and DiT-based). We find significant improvements even over previous per-query personalization methods.
Authors: Shanle Yao, Ghazal Alinezhad Noghre, Armin Danesh Pazho, Hamed Tabkhi
Abstract: Video Anomaly Detection (VAD) can play a key role in spotting unusual activities in video footage. VAD is difficult to use in real-world settings due to the dynamic nature of human actions, environmental variations, and domain shifts. Traditional evaluation metrics often prove inadequate for such scenarios, as they rely on static assumptions and fall short of identifying a threshold that distinguishes normal from anomalous behavior in dynamic settings. To address this, we introduce an active learning framework tailored for VAD, designed for adapting to the ever-changing real-world conditions. Our approach leverages active learning to continuously select the most informative data points for labeling, thereby enhancing model adaptability. A critical innovation is the incorporation of a human-in-the-loop mechanism, which enables the identification of actual normal and anomalous instances from pseudo-labeling results generated by AI. This collected data allows the framework to define an adaptive threshold tailored to different environments, ensuring that the system remains effective as the definition of 'normal' shifts across various settings. Implemented within a lab-based framework that simulates real-world conditions, our approach allows rigorous testing and refinement of VAD algorithms with a new metric. Experimental results show that our method achieves an EBI (Error Balance Index) of 68.91 for Q3 in real-world simulated scenarios, demonstrating its practical effectiveness and significantly enhancing the applicability of VAD in dynamic environments.
Authors: Fuhao Chang, Shuxin Li, Yabei Li, Lei He
Abstract: Open-set perception in complex traffic environments poses a critical challenge for autonomous driving systems, particularly in identifying previously unseen object categories, which is vital for ensuring safety. Visual Language Models (VLMs), with their rich world knowledge and strong semantic reasoning capabilities, offer new possibilities for addressing this task. However, existing approaches typically leverage VLMs to extract visual features and couple them with traditional object detectors, resulting in multi-stage error propagation that hinders perception accuracy. To overcome this limitation, we propose VLM-3D, the first end-to-end framework that enables VLMs to perform 3D geometric perception in autonomous driving scenarios. VLM-3D incorporates Low-Rank Adaptation (LoRA) to efficiently adapt VLMs to driving tasks with minimal computational overhead, and introduces a joint semantic-geometric loss design: token-level semantic loss is applied during early training to ensure stable convergence, while 3D IoU loss is introduced in later stages to refine the accuracy of 3D bounding box predictions. Evaluations on the nuScenes dataset demonstrate that the proposed joint semantic-geometric loss in VLM-3D leads to a 12.8% improvement in perception accuracy, fully validating the effectiveness and advancement of our method.
Authors: Yuqi Li, Haotian Zhang, Li Li, Dong Liu, Feng Wu
Abstract: Recent advances in large language models (LLMs) highlight a strong connection between intelligence and compression. Learned image compression, a fundamental task in modern data compression, has made significant progress in recent years. However, current models remain limited in scale, restricting their representation capacity, and how scaling model size influences compression performance remains unexplored. In this work, we present a pioneering study on scaling up learned image compression models and revealing the performance trends through scaling laws. Using the recent state-of-the-art HPCM model as baseline, we scale model parameters from 68.5 millions to 1 billion and fit power-law relations between test loss and key scaling variables, including model size and optimal training compute. The results reveal a scaling trend, enabling extrapolation to larger scale models. Experimental results demonstrate that the scaled-up HPCM-1B model achieves state-of-the-art rate-distortion performance. We hope this work inspires future exploration of large-scale compression models and deeper investigations into the connection between compression and intelligence.
Authors: Ahsan Habib Akash, Greg Murray, Annahita Amireskandari, Joel Palko, Carol Laxson, Binod Bhattarai, Prashnna Gyawali
Abstract: Vision-Language Models (VLMs) have achieved remarkable success on multimodal tasks such as image-text retrieval and zero-shot classification, yet they can exhibit demographic biases even when explicit protected attributes are absent during training. In this work, we focus on automated glaucoma screening from retinal fundus images, a critical application given that glaucoma is a leading cause of irreversible blindness and disproportionately affects underserved populations. Building on a reweighting-based contrastive learning framework, we introduce an attribute-agnostic debiasing method that (i) infers proxy subgroups via unsupervised clustering of image-image embeddings, (ii) computes gradient-similarity weights between the CLIP-style multimodal loss and a SimCLR-style image-pair contrastive loss, and (iii) applies these weights in a joint, top-$k$ weighted objective to upweight underperforming clusters. This label-free approach adaptively targets the hardest examples, thereby reducing subgroup disparities. We evaluate our method on the Harvard FairVLMed glaucoma subset, reporting Equalized Odds Distance (EOD), Equalized Subgroup AUC (ES AUC), and Groupwise AUC to demonstrate equitable performance across inferred demographic subgroups.
Authors: Oleksandr Kuznetsov, Emanuele Frontoni, Luca Romeo, Riccardo Rosati, Andrea Maranesi, Alessandro Muscatello
Abstract: In the rapidly evolving landscape of digital security, biometric authentication systems, particularly facial recognition, have emerged as integral components of various security protocols. However, the reliability of these systems is compromised by sophisticated spoofing attacks, where imposters gain unauthorized access by falsifying biometric traits. Current literature reveals a concerning gap: existing liveness detection methodologies - designed to counteract these breaches - fall short against advanced spoofing tactics employing deepfakes and other artificial intelligence-driven manipulations. This study introduces a robust solution through novel deep learning models addressing the deficiencies in contemporary anti-spoofing techniques. By innovatively integrating texture analysis and reflective properties associated with genuine human traits, our models distinguish authentic presence from replicas with remarkable precision. Extensive evaluations were conducted across five diverse datasets, encompassing a wide range of attack vectors and environmental conditions. Results demonstrate substantial advancement over existing systems, with our best model (AttackNet V2.2) achieving 99.9% average accuracy when trained on combined data. Moreover, our research unveils critical insights into the behavioral patterns of impostor attacks, contributing to a more nuanced understanding of their evolving nature. The implications are profound: our models do not merely fortify the authentication processes but also instill confidence in biometric systems across various sectors reliant on secure access.
Authors: Ya Zou, Jingfeng Yao, Siyuan Yu, Shuai Zhang, Wenyu Liu, Xinggang Wang
Abstract: There is a growing demand for deploying large generative AI models on mobile devices. For recent popular video generative models, however, the Variational AutoEncoder (VAE) represents one of the major computational bottlenecks. Both large parameter sizes and mismatched kernels cause out-of-memory errors or extremely slow inference on mobile devices. To address this, we propose a low-cost solution that efficiently transfers widely used video VAEs to mobile devices. (1) We analyze redundancy in existing VAE architectures and get empirical design insights. By integrating 3D depthwise separable convolutions into our model, we significantly reduce the number of parameters. (2) We observe that the upsampling techniques in mainstream video VAEs are poorly suited to mobile hardware and form the main bottleneck. In response, we propose a decoupled 3D pixel shuffle scheme that slashes end-to-end delay. Building upon these, we develop a universal mobile-oriented VAE decoder, Turbo-VAED. (3) We propose an efficient VAE decoder training method. Since only the decoder is used during deployment, we distill it to Turbo-VAED instead of retraining the full VAE, enabling fast mobile adaptation with minimal performance loss. To our knowledge, our method enables real-time 720p video VAE decoding on mobile devices for the first time. This approach is widely applicable to most video VAEs. When integrated into four representative models, with training cost as low as $95, it accelerates original VAEs by up to 84.5x at 720p resolution on GPUs, uses as low as 17.5% of original parameter count, and retains 96.9% of the original reconstruction quality. Compared to mobile-optimized VAEs, Turbo-VAED achieves a 2.9x speedup in FPS and better reconstruction quality on the iPhone 16 Pro. The code and models will soon be available at https://github.com/hustvl/Turbo-VAED.
Authors: Timo Teufel, Pulkit Gera, Xilong Zhou, Umar Iqbal, Pramod Rao, Jan Kautz, Vladislav Golyanik, Christian Theobalt
Abstract: Simultaneous relighting and novel-view rendering of digital human representations is an important yet challenging task with numerous applications. Progress in this area has been significantly limited due to the lack of publicly available, high-quality datasets, especially for full-body human captures. To address this critical gap, we introduce the HumanOLAT dataset, the first publicly accessible large-scale dataset of multi-view One-Light-at-a-Time (OLAT) captures of full-body humans. The dataset includes HDR RGB frames under various illuminations, such as white light, environment maps, color gradients and fine-grained OLAT illuminations. Our evaluations of state-of-the-art relighting and novel-view synthesis methods underscore both the dataset's value and the significant challenges still present in modeling complex human-centric appearance and lighting interactions. We believe HumanOLAT will significantly facilitate future research, enabling rigorous benchmarking and advancements in both general and human-specific relighting and rendering techniques.
Authors: Yi Tang, Kaini Wang, Yang Chen, Guangquan Zhou
Abstract: Developing general artificial intelligence (AI) systems to support endoscopic image diagnosis is an emerging research priority. Existing methods based on large-scale pretraining often lack unified coordination across tasks and struggle to handle the multi-step processes required in complex clinical workflows. While AI agents have shown promise in flexible instruction parsing and tool integration across domains, their potential in endoscopy remains underexplored. To address this gap, we propose EndoAgent, the first memory-guided agent for vision-to-decision endoscopic analysis that integrates iterative reasoning with adaptive tool selection and collaboration. Built on a dual-memory design, it enables sophisticated decision-making by ensuring logical coherence through short-term action tracking and progressively enhancing reasoning acuity through long-term experiential learning. To support diverse clinical tasks, EndoAgent integrates a suite of expert-designed tools within a unified reasoning loop. We further introduce EndoAgentBench, a benchmark of 5,709 visual question-answer pairs that assess visual understanding and language generation capabilities in realistic scenarios. Extensive experiments show that EndoAgent consistently outperforms both general and medical multimodal models, exhibiting its strong flexibility and reasoning capabilities.
Authors: Ryan Mioduski
Abstract: Virginia's seventeenth- and eighteenth-century land patents survive primarily as narrative metes-and-bounds descriptions, limiting spatial analysis. This study systematically evaluates current-generation large language models (LLMs) in converting these prose abstracts into geographically accurate latitude/longitude coordinates within a focused evaluation context. A digitized corpus of 5,471 Virginia patent abstracts (1695-1732) is released, with 43 rigorously verified test cases serving as an initial, geographically focused benchmark. Six OpenAI models across three architectures (o-series, GPT-4-class, and GPT-3.5) were tested under two paradigms: direct-to-coordinate and tool-augmented chain-of-thought invoking external geocoding APIs. Results were compared with a GIS-analyst baseline, the Stanford NER geoparser, Mordecai-3, and a county-centroid heuristic. The top single-call model, o3-2025-04-16, achieved a mean error of 23 km (median 14 km), outperforming the median LLM (37.4 km) by 37.5%, the weakest LLM (50.3 km) by 53.5%, and external baselines by 67% (GIS analyst) and 70% (Stanford NER). A five-call ensemble further reduced errors to 19 km (median 12 km) at minimal additional cost (approx. USD 0.20 per grant), outperforming the median LLM by 48.6%. A patentee-name-redaction ablation increased error by about 9%, indicating reliance on textual landmark and adjacency descriptions rather than memorization. The cost-efficient gpt-4o-2024-08-06 model maintained a 28 km mean error at USD 1.09 per 1,000 grants, establishing a strong cost-accuracy benchmark; external geocoding tools offered no measurable benefit in this evaluation. These findings demonstrate the potential of LLMs for scalable, accurate, and cost-effective historical georeferencing.
Authors: Seonyoung Kim, Dongil Kim
Abstract: Deep learning has emerged as the most promising approach in various fields; however, when the distributions of training and test data are different (domain shift), the performance of deep learning models can degrade. Semi-supervised domain adaptation (SSDA) is a major approach for addressing this issue, assuming that a fully labeled training set (source domain) is available, but the test set (target domain) provides labels only for a small subset. In this study, we propose a novel two-step momentum encoder-utilized SSDA framework, MoSSDA, for multivariate time-series classification. Time series data are highly sensitive to noise, and sequential dependencies cause domain shifts resulting in critical performance degradation. To obtain a robust, domain-invariant and class-discriminative representation, MoSSDA employs a domain-invariant encoder to learn features from both source and target domains. Subsequently, the learned features are fed to a mixup-enhanced positive contrastive module consisting of an online momentum encoder. The final classifier is trained with learned features that exhibit consistency and discriminability with limited labeled target domain data, without data augmentation. We applied a two-stage process by separating the gradient flow between the encoders and the classifier to obtain rich and complex representations. Through extensive experiments on six diverse datasets, MoSSDA achieved state-of-the-art performance for three different backbones and various unlabeled ratios in the target domain data. The Ablation study confirms that each module, including two-stage learning, is effective in improving the performance. Our code is available at https://github.com/seonyoungKimm/MoSSDA
Authors: Conor Rowan, Sumedh Soman, John A. Evans
Abstract: We present a novel approach to variational volume reconstruction from sparse, noisy slice data using the Deep Ritz method. Motivated by biomedical imaging applications such as MRI-based slice-to-volume reconstruction (SVR), our approach addresses three key challenges: (i) the reliance on image segmentation to extract boundaries from noisy grayscale slice images, (ii) the need to reconstruct volumes from a limited number of slice planes, and (iii) the computational expense of traditional mesh-based methods. We formulate a variational objective that combines a regression loss designed to avoid image segmentation by operating on noisy slice data directly with a modified Cahn-Hilliard energy incorporating anisotropic diffusion to regularize the reconstructed geometry. We discretize the phase field with a neural network, approximate the objective at each optimization step with Monte Carlo integration, and use ADAM to find the minimum of the approximated variational objective. While the stochastic integration may not yield the true solution to the variational problem, we demonstrate that our method reliably produces high-quality reconstructed volumes in a matter of seconds, even when the slice data is sparse and noisy.
Authors: Mutian Tong, Rundi Wu, Changxi Zheng
Abstract: Indoor lighting estimation from a single image or video remains a challenge due to its highly ill-posed nature, especially when the lighting condition of the scene varies spatially and temporally. We propose a method that estimates from an input video a continuous light field describing the spatiotemporally varying lighting of the scene. We leverage 2D diffusion priors for optimizing such light field represented as a MLP. To enable zero-shot generalization to in-the-wild scenes, we fine-tune a pre-trained image diffusion model to predict lighting at multiple locations by jointly inpainting multiple chrome balls as light probes. We evaluate our method on indoor lighting estimation from a single image or video and show superior performance over compared baselines. Most importantly, we highlight results on spatiotemporally consistent lighting estimation from in-the-wild videos, which is rarely demonstrated in previous works.
Authors: Dalton Omens, Allise Thurman, Jihun Yu, Ronald Fedkiw
Abstract: In this paper, we consider retargeting a tracked facial performance to either another person or to a virtual character in a game or virtual reality (VR) environment. We remove the difficulties associated with identifying and retargeting the semantics of one rig framework to another by utilizing the same framework (3DMM, FLAME, MetaHuman, etc.) for both subjects. Although this does not constrain the choice of framework when retargeting from one person to another, it does force the tracker to use the game/VR character rig when retargeting to a game/VR character. We utilize volumetric morphing in order to fit facial rigs to both performers and targets; in addition, a carefully chosen set of Simon-Says expressions is used to calibrate each rig to the motion signatures of the relevant performer or target. Although a uniform set of Simon-Says expressions can likely be used for all person to person retargeting, we argue that person to game/VR character retargeting benefits from Simon-Says expressions that capture the distinct motion signature of the game/VR character rig. The Simon-Says calibrated rigs tend to produce the desired expressions when exercising animation controls (as expected). Unfortunately, these well-calibrated rigs still lead to undesirable controls when tracking a performance (a well-behaved function can have an arbitrarily ill-conditioned inverse), even though they typically produce acceptable geometry reconstructions. Thus, we propose a fine-tuning approach that modifies the rig used by the tracker in order to promote the output of more semantically meaningful animation controls, facilitating high efficacy retargeting. In order to better address real-world scenarios, the fine-tuning relies on implicit differentiation so that the tracker can be treated as a (potentially non-differentiable) black box.
Authors: Praveen Sumanasekara, Athulya Ratnayake, Buddhi Wijenayake, Keshawa Ratnayake, Roshan Godaliyadda, Parakrama Ekanayake, Vijitha Herath
Abstract: Spectral variability significantly impacts the accuracy and convergence of hyperspectral unmixing algorithms. While many methods address complex spectral variability, large-scale variations in spectral signature scale caused by factors such as topography, illumination, and shadowing remain a major challenge. These variations often degrade unmixing performance and complicate model fitting. In this paper, we propose a novel preprocessing algorithm that corrects scale-induced spectral variability prior to unmixing. By isolating and compensating for these large-scale multiplicative effects, the algorithm provides a cleaner input, enabling unmixing methods to focus more effectively on modeling nonlinear spectral variability and abundance estimation. We present a rigorous mathematical framework to describe scale variability and extensive experimental validation of the proposed algorithm. Furthermore, the algorithm's impact is evaluated across a broad spectrum of state-of-the-art unmixing algorithms on two synthetic and two real hyperspectral datasets. The proposed preprocessing step consistently improves the performance of these algorithms, including those specifically designed to handle spectral variability, with error reductions close to 50% in many cases. This demonstrates that scale correction acts as a complementary step, facilitating more accurate unmixing by existing methods. The algorithm's generality and significant impact highlight its potential as a key component in practical hyperspectral unmixing pipelines. The implementation code will be made publicly available upon publication.
Authors: Nastaran Ghorbani, Bitasadat Jamshidi, Mohsen Rostamy-Malkhalifeh
Abstract: Liver cancer is one of the most prevalent and lethal forms of cancer, making early detection crucial for effective treatment. This paper introduces a novel approach for automated liver tumor segmentation in computed tomography (CT) images by integrating a 3D U-Net architecture with the Bat Algorithm for hyperparameter optimization. The method enhances segmentation accuracy and robustness by intelligently optimizing key parameters like the learning rate and batch size. Evaluated on a publicly available dataset, our model demonstrates a strong ability to balance precision and recall, with a high F1-score at lower prediction thresholds. This is particularly valuable for clinical diagnostics, where ensuring no potential tumors are missed is paramount. Our work contributes to the field of medical image analysis by demonstrating that the synergy between a robust deep learning architecture and a metaheuristic optimization algorithm can yield a highly effective solution for complex segmentation tasks.
Authors: Ilerioluwakiiye Abolade, Emmanuel Idoko, Solomon Odelola, Promise Omoigui, Adetola Adebanwo, Aondana Iorumbur, Udunna Anazodo, Alessandro Crimi, Raymond Confidence
Abstract: Pediatric chest X-ray imaging is essential for early diagnosis, particularly in low-resource settings where advanced imaging modalities are often inaccessible. Low-dose protocols reduce radiation exposure in children but introduce substantial noise that can obscure critical anatomical details. Conventional denoising methods often degrade fine details, compromising diagnostic accuracy. In this paper, we present SharpXR, a structure-aware dual-decoder U-Net designed to denoise low-dose pediatric X-rays while preserving diagnostically relevant features. SharpXR combines a Laplacian-guided edge-preserving decoder with a learnable fusion module that adaptively balances noise suppression and structural detail retention. To address the scarcity of paired training data, we simulate realistic Poisson-Gaussian noise on the Pediatric Pneumonia Chest X-ray dataset. SharpXR outperforms state-of-the-art baselines across all evaluation metrics while maintaining computational efficiency suitable for resource-constrained settings. SharpXR-denoised images improved downstream pneumonia classification accuracy from 88.8% to 92.5%, underscoring its diagnostic value in low-resource pediatric care.
Authors: Dasith de Silva Edirimuni, Xuequan Lu, Ajmal Saeed Mian, Lei Wei, Gang Li, Scott Schaefer, Ying He
Abstract: Point cloud capture processes are error-prone and introduce noisy artifacts that necessitate filtering/denoising. Recent filtering methods often suffer from point clustering or noise retaining issues. In this paper, we propose Hybrid Point Cloud Filtering ($\textbf{HybridPF}$) that considers both short-range and long-range filtering trajectories when removing noise. It is well established that short range scores, given by $\nabla_{x}\log p(x_t)$, may provide the necessary displacements to move noisy points to the underlying clean surface. By contrast, long range velocity flows approximate constant displacements directed from a high noise variant patch $x_0$ towards the corresponding clean surface $x_1$. Here, noisy patches $x_t$ are viewed as intermediate states between the high noise variant and the clean patches. Our intuition is that long range information from velocity flow models can guide the short range scores to align more closely with the clean points. In turn, score models generally provide a quicker convergence to the clean surface. Specifically, we devise two parallel modules, the ShortModule and LongModule, each consisting of an Encoder-Decoder pair to respectively account for short-range scores and long-range flows. We find that short-range scores, guided by long-range features, yield filtered point clouds with good point distributions and convergence near the clean surface. We design a joint loss function to simultaneously train the ShortModule and LongModule, in an end-to-end manner. Finally, we identify a key weakness in current displacement based methods, limitations on the decoder architecture, and propose a dynamic graph convolutional decoder to improve the inference process. Comprehensive experiments demonstrate that our HybridPF achieves state-of-the-art results while enabling faster inference speed.
Authors: Shibin Su, Guoqiang Liang, De Cheng, Shizhou Zhang, Lingyan Ran, Yanning Zhang
Abstract: Online Class-Incremental Learning (OCIL) enables models to learn continuously from non-i.i.d. data streams and samples of the data streams can be seen only once, making it more suitable for real-world scenarios compared to offline learning. However, OCIL faces two key challenges: maintaining model stability under strict memory constraints and ensuring adaptability to new tasks. Under stricter memory constraints, current replay-based methods are less effective. While ensemble methods improve adaptability (plasticity), they often struggle with stability. To overcome these challenges, we propose a novel approach that enhances ensemble learning through a Global Workspace Model (GWM)-a shared, implicit memory that guides the learning of multiple student models. The GWM is formed by fusing the parameters of all students within each training batch, capturing the historical learning trajectory and serving as a dynamic anchor for knowledge consolidation. This fused model is then redistributed periodically to the students to stabilize learning and promote cross-task consistency. In addition, we introduce a multi-level collaborative distillation mechanism. This approach enforces peer-to-peer consistency among students and preserves historical knowledge by aligning each student with the GWM. As a result, student models remain adaptable to new tasks while maintaining previously learned knowledge, striking a better balance between stability and plasticity. Extensive experiments on three standard OCIL benchmarks show that our method delivers significant performance improvement for several OCIL models across various memory budgets.
Authors: Chen Li, Han Zhang, Zhantao Yang, Fangyi Chen, Zihan Wang, Anudeepsekhar Bolimera, Marios Savvides
Abstract: Vision-language models (VLMs) have made significant strides in reasoning, yet they often struggle with complex multimodal tasks and tend to generate overly verbose outputs. A key limitation is their reliance on chain-of-thought (CoT) reasoning, despite many tasks benefiting from alternative topologies like trees or graphs. To address this, we introduce STELAR-Vision, a training framework for topology-aware reasoning. At its core is TopoAug, a synthetic data pipeline that enriches training with diverse topological structures. Using supervised fine-tuning and reinforcement learning, we post-train Qwen2VL models with both accuracy and efficiency in mind. Additionally, we propose Frugal Learning, which reduces output length with minimal accuracy loss. On MATH-V and VLM-S2H, STELAR-Vision improves accuracy by 9.7% over its base model and surpasses the larger Qwen2VL-72B-Instruct by 7.3%. On five out-of-distribution benchmarks, it outperforms Phi-4-Multimodal-Instruct by up to 28.4% and LLaMA-3.2-11B-Vision-Instruct by up to 13.2%, demonstrating strong generalization. Compared to Chain-Only training, our approach achieves 4.3% higher overall accuracy on in-distribution datasets and consistently outperforms across all OOD benchmarks. We have released datasets, and code will be available.
Authors: Qianru Qiu, Jiafeng Mao, Xueting Wang
Abstract: With the advent of diffusion models, Text-to-Image (T2I) generation has seen substantial advancements. Current T2I models allow users to specify object colors using linguistic color names, and some methods aim to personalize color-object association through prompt learning. However, existing models struggle to provide comprehensive control over the color schemes of an entire image, especially for background elements and less prominent objects not explicitly mentioned in prompts. This paper proposes a novel approach to enhance color scheme control by integrating color palettes as a separate guidance mechanism alongside prompt instructions. We investigate the effectiveness of palette guidance by exploring various palette representation methods within a diffusion-based image colorization framework. To facilitate this exploration, we construct specialized palette-text-image datasets and conduct extensive quantitative and qualitative analyses. Our results demonstrate that incorporating palette guidance significantly improves the model's ability to generate images with desired color schemes, enabling a more controlled and refined colorization process.
Authors: Mustafa Akben, Vinayaka Gude, Haya Ajjan
Abstract: The ability to discern subtle emotional cues is fundamental to human social intelligence. As artificial intelligence (AI) becomes increasingly common, AI's ability to recognize and respond to human emotions is crucial for effective human-AI interactions. In particular, whether such systems can match or surpass human experts remains to be seen. However, the emotional intelligence of AI, particularly multimodal large language models (MLLMs), remains largely unexplored. This study evaluates the emotion recognition abilities of MLLMs using the Reading the Mind in the Eyes Test (RMET) and its multiracial counterpart (MRMET), and compares their performance against human participants. Results show that, on average, MLLMs outperform humans in accurately identifying emotions across both tests. This trend persists even when comparing performance across low, medium, and expert-level performing groups. Yet when we aggregate independent human decisions to simulate collective intelligence, human groups significantly surpass the performance of aggregated MLLM predictions, highlighting the wisdom of the crowd. Moreover, a collaborative approach (augmented intelligence) that combines human and MLLM predictions achieves greater accuracy than either humans or MLLMs alone. These results suggest that while MLLMs exhibit strong emotion recognition at the individual level, the collective intelligence of humans and the synergistic potential of human-AI collaboration offer the most promising path toward effective emotional AI. We discuss the implications of these findings for the development of emotionally intelligent AI systems and future research directions.
Authors: Bo-Hsun Chen, Nevindu M. Batagoda, Dan Negrut
Abstract: We introduce DiffPhysCam, a differentiable camera simulator designed to support robotics and embodied AI applications by enabling gradient-based optimization in visual perception pipelines. Generating synthetic images that closely mimic those from real cameras is essential for training visual models and enabling end-to-end visuomotor learning. Moreover, differentiable rendering allows inverse reconstruction of real-world scenes as digital twins, facilitating simulation-based robotics training. However, existing virtual cameras offer limited control over intrinsic settings, poorly capture optical artifacts, and lack tunable calibration parameters -- hindering sim-to-real transfer. DiffPhysCam addresses these limitations through a multi-stage pipeline that provides fine-grained control over camera settings, models key optical effects such as defocus blur, and supports calibration with real-world data. It enables both forward rendering for image synthesis and inverse rendering for 3D scene reconstruction, including mesh and material texture optimization. We show that DiffPhysCam enhances robotic perception performance in synthetic image tasks. As an illustrative example, we create a digital twin of a real-world scene using inverse rendering, simulate it in a multi-physics environment, and demonstrate navigation of an autonomous ground vehicle using images generated by DiffPhysCam.
Authors: Yingxue Pang, Shijie Zhao, Haiqiang Wang, Gen Zhan, Junlin Li, Li Zhang
Abstract: Sharpening is a widely adopted technique to improve video quality, which can effectively emphasize textures and alleviate blurring. However, increasing the sharpening level comes with a higher video bitrate, resulting in degraded Quality of Service (QoS). Furthermore, the video quality does not necessarily improve with increasing sharpening levels, leading to issues such as over-sharpening. Clearly, it is essential to figure out how to boost video quality with a proper sharpening level while also controlling bandwidth costs effectively. This paper thus proposes a novel Frequency-assisted Sharpening level Prediction model (FreqSP). We first label each video with the sharpening level correlating to the optimal bitrate and quality tradeoff as ground truth. Then taking uncompressed source videos as inputs, the proposed FreqSP leverages intricate CNN features and high-frequency components to estimate the optimal sharpening level. Extensive experiments demonstrate the effectiveness of our method.
Authors: Xiang Zhang, Yawar Siddiqui, Armen Avetisyan, Chris Xie, Jakob Engel, Henry Howard-Jenkins
Abstract: We introduce VertexRegen, a novel mesh generation framework that enables generation at a continuous level of detail. Existing autoregressive methods generate meshes in a partial-to-complete manner and thus intermediate steps of generation represent incomplete structures. VertexRegen takes inspiration from progressive meshes and reformulates the process as the reversal of edge collapse, i.e. vertex split, learned through a generative model. Experimental results demonstrate that VertexRegen produces meshes of comparable quality to state-of-the-art methods while uniquely offering anytime generation with the flexibility to halt at any step to yield valid meshes with varying levels of detail.
Authors: Conall Daly, Anil Kokaram
Abstract: Many methods exist for frame synthesis in image sequences but can be broadly categorised into frame interpolation and view synthesis techniques. Fundamentally, both frame interpolation and view synthesis tackle the same task, interpolating a frame given surrounding frames in time or space. However, most frame interpolation datasets focus on temporal aspects with single cameras moving through time and space, while view synthesis datasets are typically biased toward stereoscopic depth estimation use cases. This makes direct comparison between view synthesis and frame interpolation methods challenging. In this paper, we develop a novel multi-camera dataset using a custom-built dense linear camera array to enable fair comparison between these approaches. We evaluate classical and deep learning frame interpolators against a view synthesis method (3D Gaussian Splatting) for the task of view in-betweening. Our results reveal that deep learning methods do not significantly outperform classical methods on real image data, with 3D Gaussian Splatting actually underperforming frame interpolators by as much as 3.5 dB PSNR. However, in synthetic scenes, the situation reverses -- 3D Gaussian Splatting outperforms frame interpolation algorithms by almost 5 dB PSNR at a 95% confidence level.
Authors: Conall Daly, Darren Ramsook, Anil Kokaram
Abstract: Video frame interpolation (VFI) offers a way to generate intermediate frames between consecutive frames of a video sequence. Although the development of advanced frame interpolation algorithms has received increased attention in recent years, assessing the perceptual quality of interpolated content remains an ongoing area of research. In this paper, we investigate simple ways to process motion fields, with the purposes of using them as video quality metric for evaluating frame interpolation algorithms. We evaluate these quality metrics using the BVI-VFI dataset which contains perceptual scores measured for interpolated sequences. From our investigation we propose a motion metric based on measuring the divergence of motion fields. This metric correlates reasonably with these perceptual scores (PLCC=0.51) and is more computationally efficient (x2.7 speedup) compared to FloLPIPS (a well known motion-based metric). We then use our new proposed metrics to evaluate a range of state of the art frame interpolation metrics and find our metrics tend to favour more perceptual pleasing interpolated frames that may not score highly in terms of PSNR or SSIM.
Authors: Xinyuan Wang, Bowen Wang, Dunjie Lu, Junlin Yang, Tianbao Xie, Junli Wang, Jiaqi Deng, Xiaole Guo, Yiheng Xu, Chen Henry Wu, Zhennan Shen, Zhuokai Li, Ryan Li, Xiaochuan Li, Junda Chen, Boyuan Zheng, Peihang Li, Fangyu Lei, Ruisheng Cao, Yeqiao Fu, Dongchan Shin, Martin Shin, Jiarui Hu, Yuyan Wang, Jixuan Chen, Yuxiao Ye, Danyang Zhang, Dikang Du, Hao Hu, Huarong Chen, Zaida Zhou, Yipu Wang, Heng Wang, Diyi Yang, Victor Zhong, Flood Sung, Y. Charles, Zhilin Yang, Tao Yu
Abstract: Vision-language models have demonstrated impressive capabilities as computer-use agents (CUAs) capable of automating diverse computer tasks. As their commercial potential grows, critical details of the most capable CUA systems remain closed. As these agents will increasingly mediate digital interactions and execute consequential decisions on our behalf, the research community needs access to open CUA frameworks to study their capabilities, limitations, and risks. To bridge this gap, we propose OpenCUA, a comprehensive open-source framework for scaling CUA data and foundation models. Our framework consists of: (1) an annotation infrastructure that seamlessly captures human computer-use demonstrations; (2) AgentNet, the first large-scale computer-use task dataset spanning 3 operating systems and 200+ applications and websites; (3) a scalable pipeline that transforms demonstrations into state-action pairs with reflective long Chain-of-Thought reasoning that sustain robust performance gains as data scales. Our end-to-end agent models demonstrate strong performance across CUA benchmarks. In particular, OpenCUA-32B achieves an average success rate of 34.8% on OSWorld-Verified, establishing a new state-of-the-art (SOTA) among open-source models and surpassing OpenAI CUA (GPT-4o). Further analysis confirms that our approach generalizes well across domains and benefits significantly from increased test-time computation. We release our annotation tool, datasets, code, and models to build open foundations for further CUA research.
Authors: Zixin Yin, Xili Dai, Ling-Hao Chen, Deyu Zhou, Jianan Wang, Duomin Wang, Gang Yu, Lionel M. Ni, Lei Zhang, Heung-Yeung Shum
Abstract: Text-guided color editing in images and videos is a fundamental yet unsolved problem, requiring fine-grained manipulation of color attributes, including albedo, light source color, and ambient lighting, while preserving physical consistency in geometry, material properties, and light-matter interactions. Existing training-free methods offer broad applicability across editing tasks but struggle with precise color control and often introduce visual inconsistency in both edited and non-edited regions. In this work, we present ColorCtrl, a training-free color editing method that leverages the attention mechanisms of modern Multi-Modal Diffusion Transformers (MM-DiT). By disentangling structure and color through targeted manipulation of attention maps and value tokens, our method enables accurate and consistent color editing, along with word-level control of attribute intensity. Our method modifies only the intended regions specified by the prompt, leaving unrelated areas untouched. Extensive experiments on both SD3 and FLUX.1-dev demonstrate that ColorCtrl outperforms existing training-free approaches and achieves state-of-the-art performances in both edit quality and consistency. Furthermore, our method surpasses strong commercial models such as FLUX.1 Kontext Max and GPT-4o Image Generation in terms of consistency. When extended to video models like CogVideoX, our approach exhibits greater advantages, particularly in maintaining temporal coherence and editing stability. Finally, our method also generalizes to instruction-based editing diffusion models such as Step1X-Edit and FLUX.1 Kontext dev, further demonstrating its versatility.
Authors: Anguelos Nicolaou, Daniel Luger, Franziska Decker, Nicolas Renet, Vincent Christlein, Georg Vogeler
Abstract: Diplomatics, the analysis of medieval charters, is a major field of research in which paleography is applied. Annotating data, if performed by laymen, needs validation and correction by experts. In this paper, we propose an effective and efficient annotation approach for charter segmentation, essentially reducing it to object detection. This approach allows for a much more efficient use of the paleographer's time and produces results that can compete and even outperform pixel-level segmentation in some use cases. Further experiments shed light on how to design a class ontology in order to make the best use of annotators' time and effort. Exploiting the presence of calibration cards in the image, we further annotate the data with the physical length in pixels and train regression neural networks to predict it from image patches.
Authors: Xuyang Chen, Dong Wang, Konrad Schindler, Mingwei Sun, Yongliang Wang, Nicolo Savioli, Liqiu Meng
Abstract: Recently, Transformer-based text detection techniques have sought to predict polygons by encoding the coordinates of individual boundary vertices using distinct query features. However, this approach incurs a significant memory overhead and struggles to effectively capture the intricate relationships between vertices belonging to the same instance. Consequently, irregular text layouts often lead to the prediction of outlined vertices, diminishing the quality of results. To address these challenges, we present an innovative approach rooted in Sparse R-CNN: a cascade decoding pipeline for polygon prediction. Our method ensures precision by iteratively refining polygon predictions, considering both the scale and location of preceding results. Leveraging this stabilized regression pipeline, even employing just a single feature vector to guide polygon instance regression yields promising detection results. Simultaneously, the leverage of instance-level feature proposal substantially enhances memory efficiency (>50% less vs. the state-of-the-art method DPText-DETR) and reduces inference speed (>40% less vs. DPText-DETR) with minor performance drop on benchmarks.
Authors: Qiao Yang, Yu Zhang, Yutong Chen, Jian Zhang, Shunli Zhang
Abstract: Most existing learning-based multi-modality image fusion (MMIF) methods suffer from significant structure inconsistency due to their inappropriate usage of structural features at the semantic level. To alleviate these issues, we propose a semantic structure-preserving fusion approach for MMIF, namely SSPFusion. At first, we design a structural feature extractor (SFE) to extract the prominent structural features from multiple input images. Concurrently, we introduce a transformation function with Sobel operator to generate self-supervised structural signals in these extracted features. Subsequently, we design a multi-scale structure-preserving fusion (SPF) module, guided by the generated structural signals, to merge the structural features of input images. This process ensures the preservation of semantic structure consistency between the resultant fusion image and the input images. Through the synergy of these two robust modules of SFE and SPF, our method can generate high-quality fusion images and demonstrate good generalization ability. Experimental results, on both infrared-visible image fusion and medical image fusion tasks, demonstrate that our method outperforms nine state-of-the-art methods in terms of both qualitative and quantitative evaluations. The code is publicly available at https://github.com/QiaoYang-CV/SSPFUSION.
Authors: Ziyun Wang, Jinyuan Guo, Kostas Daniilidis
Abstract: Event cameras are a novel type of biologically inspired vision sensor known for their high temporal resolution, high dynamic range, and low power consumption. Because of these properties, they are well-suited for processing fast motions that require rapid reactions. Although event cameras have recently shown competitive performance in unsupervised optical flow estimation, performance in detecting independently moving objects (IMOs) is lacking behind, although event-based methods would be suited for this task based on their low latency and HDR properties. Previous approaches to event-based IMO segmentation have been heavily dependent on labeled data. However, biological vision systems have developed the ability to avoid moving objects through daily tasks without being given explicit labels. In this work, we propose the first event framework that generates IMO pseudo-labels using geometric constraints. Due to its unsupervised nature, our method can handle an arbitrary number of not predetermined objects and is easily scalable to datasets where expensive IMO labels are not readily available. We evaluate our approach on the EVIMO dataset and show that it performs competitively with supervised methods, both quantitatively and qualitatively.
Authors: Shanle Yao, Babak Rahimi Ardabili, Armin Danesh Pazho, Ghazal Alinezhad Noghre, Christopher Neff, Lauren Bourque, Hamed Tabkhi
Abstract: This article adopts and evaluates an AI-enabled Smart Video Solution (SVS) designed to enhance safety in the real world. The system integrates with existing infrastructure camera networks, leveraging recent advancements in AI for easy adoption. Prioritizing privacy and ethical standards, pose based data is used for downstream AI tasks such as anomaly detection. Cloud-based infrastructure and mobile app are deployed, enabling real-time alerts within communities. The SVS employs innovative data representation and visualization techniques, such as the Occupancy Indicator, Statistical Anomaly Detection, Bird's Eye View, and Heatmaps, to understand pedestrian behaviors and enhance public safety. Evaluation of the SVS demonstrates its capacity to convert complex computer vision outputs into actionable insights for stakeholders, community partners, law enforcement, urban planners, and social scientists. This article presents a comprehensive real-world deployment and evaluation of the SVS, implemented in a community college environment across 16 cameras. The system integrates AI-driven visual processing, supported by statistical analysis, database management, cloud communication, and user notifications. Additionally, the article evaluates the end-to-end latency from the moment an AI algorithm detects anomalous behavior in real-time at the camera level to the time stakeholders receive a notification. The results demonstrate the system's robustness, effectively managing 16 CCTV cameras with a consistent throughput of 16.5 frames per second (FPS) over a 21-hour period and an average end-to-end latency of 26.76 seconds between anomaly detection and alert issuance.
Authors: Qiao Yu, Xianzhi Li, Yuan Tang, Xu Han, Jinfeng Xu, Long Hu, Min Chen
Abstract: Faithfully reconstructing textured meshes is crucial for many applications. Compared to text or image modalities, leveraging 3D colored point clouds as input (colored-PC-to-mesh) offers inherent advantages in comprehensively and precisely replicating the target object's 360{\deg} characteristics. While most existing colored-PC-to-mesh methods suffer from blurry textures or require hard-to-acquire 3D training data, we propose PointDreamer, a novel framework that harnesses 2D diffusion prior for superior texture quality. Crucially, unlike prior 2D-diffusion-for-3D works driven by text or image inputs, PointDreamer successfully adapts 2D diffusion models to 3D point cloud data by a novel project-inpaint-unproject pipeline. Specifically, it first projects the point cloud into sparse 2D images and then performs diffusion-based inpainting. After that, diverging from most existing 3D reconstruction or generation approaches that predict texture in 3D/UV space thus often yielding blurry texture, PointDreamer achieves high-quality texture by directly unprojecting the inpainted 2D images to the 3D mesh. Furthermore, we identify for the first time a typical kind of unprojection artifact appearing in occlusion borders, which is common in other multiview-image-to-3D pipelines but less-explored. To address this, we propose a novel solution named the Non-Border-First (NBF) unprojection strategy. Extensive qualitative and quantitative experiments on various synthetic and real-scanned datasets demonstrate that PointDreamer, though zero-shot, exhibits SoTA performance (30% improvement on LPIPS score from 0.118 to 0.068), and is robust to noisy, sparse, or even incomplete input data. Code at: https://github.com/YuQiao0303/PointDreamer.
Authors: Huiguo He, Huan Yang, Zixi Tuo, Yuan Zhou, Qiuyue Wang, Yuhang Zhang, Zeyu Liu, Wenhao Huang, Hongyang Chao, Jian Yin
Abstract: Story visualization aims to create visually compelling images or videos corresponding to textual narratives. Despite recent advances in diffusion models yielding promising results, existing methods still struggle to create a coherent sequence of subject-consistent frames based solely on a story. To this end, we propose DreamStory, an automatic open-domain story visualization framework by leveraging the LLMs and a novel multi-subject consistent diffusion model. DreamStory consists of (1) an LLM acting as a story director and (2) an innovative Multi-Subject consistent Diffusion model (MSD) for generating consistent multi-subject across the images. First, DreamStory employs the LLM to generate descriptive prompts for subjects and scenes aligned with the story, annotating each scene's subjects for subsequent subject-consistent generation. Second, DreamStory utilizes these detailed subject descriptions to create portraits of the subjects, with these portraits and their corresponding textual information serving as multimodal anchors (guidance). Finally, the MSD uses these multimodal anchors to generate story scenes with consistent multi-subject. Specifically, the MSD includes Masked Mutual Self-Attention (MMSA) and Masked Mutual Cross-Attention (MMCA) modules. MMSA and MMCA modules ensure appearance and semantic consistency with reference images and text, respectively. Both modules employ masking mechanisms to prevent subject blending. To validate our approach and promote progress in story visualization, we established a benchmark, DS-500, which can assess the overall performance of the story visualization framework, subject-identification accuracy, and the consistency of the generation model. Extensive experiments validate the effectiveness of DreamStory in both subjective and objective evaluations. Please visit our project homepage at https://dream-xyz.github.io/dreamstory.
Authors: Phuc D. A. Nguyen, Minh Luu, Anh Tran, Cuong Pham, Khoi Nguyen
Abstract: Open-Vocab 3D Instance Segmentation methods (OV-3DIS) have recently demonstrated their ability to generalize to unseen objects. However, these methods still depend on predefined class names during testing, restricting the autonomy of agents. To mitigate this constraint, we propose a novel problem termed Open-Ended 3D Instance Segmentation (OE-3DIS), which eliminates the necessity for predefined class names during testing. Moreover, we contribute a comprehensive set of strong baselines, derived from OV-3DIS approaches and leveraging 2D Multimodal Large Language Models. To assess the performance of our OE-3DIS system, we introduce a novel Open-Ended score, evaluating both the semantic and geometric quality of predicted masks and their associated class names, alongside the standard AP score. Our approach demonstrates significant performance improvements over the baselines on the ScanNet200 and ScanNet++ datasets. Remarkably, our method surpasses the performance of Open3DIS, the current state-of-the-art method in OV-3DIS, even in the absence of ground-truth object class names.
Authors: Xuanmeng Sha, Liyun Zhang, Tomohiro Mashita, Naoya Chiba, Yuki Uranishi
Abstract: Audio-driven 3D facial animation has achieved significant progress in both research and applications. While recent baselines struggle to generate natural and continuous facial movements due to their frame-by-frame vertex generation approach, we propose 3DFacePolicy, a pioneer work that introduces a novel definition of vertex trajectory changes across consecutive frames through the concept of "action". By predicting action sequences for each vertex that encode frame-to-frame movements, we reformulate vertex generation approach into an action-based control paradigm. Specifically, we leverage a robotic control mechanism, diffusion policy, to predict action sequences conditioned on both audio and vertex states. Extensive experiments on VOCASET and BIWI datasets demonstrate that our approach significantly outperforms state-of-the-art methods and is particularly expert in dynamic, expressive and naturally smooth facial animations.
Authors: Xilin He, Cheng Luo, Xiaole Xian, Bing Li, Muhammad Haris Khan, Zongyuan Ge, Weicheng Xie, Siyang Song, Linlin Shen, Bernard Ghanem, Xiangyu Yue
Abstract: Facial expression datasets remain limited in scale due to the subjectivity of annotations and the labor-intensive nature of data collection. This limitation poses a significant challenge for developing modern deep learning-based facial expression analysis models, particularly foundation models, that rely on large-scale data for optimal performance. To tackle the overarching and complex challenge, instead of introducing a new large-scale dataset, we introduce SynFER (Synthesis of Facial Expressions with Refined Control), a novel synthetic framework for synthesizing facial expression image data based on high-level textual descriptions as well as more fine-grained and precise control through facial action units. To ensure the quality and reliability of the synthetic data, we propose a semantic guidance technique to steer the generation process and a pseudo-label generator to help rectify the facial expression labels for the synthetic images. To demonstrate the generation fidelity and the effectiveness of the synthetic data from SynFER, we conduct extensive experiments on representation learning using both synthetic data and real-world data. Results validate the efficacy of our approach and the synthetic data. Notably, our approach achieves a 67.23% classification accuracy on AffectNet when training solely with synthetic data equivalent to the AffectNet training set size, which increases to 69.84% when scaling up to five times the original size. Code is available here.
Authors: Junjun Jiang, Zengyuan Zuo, Gang Wu, Kui Jiang, Xianming Liu
Abstract: Image restoration (IR) seeks to recover high-quality images from degraded observations caused by a wide range of factors, including noise, blur, compression, and adverse weather. While traditional IR methods have made notable progress by targeting individual degradation types, their specialization often comes at the cost of generalization, leaving them ill-equipped to handle the multifaceted distortions encountered in real-world applications. In response to this challenge, the all-in-one image restoration (AiOIR) paradigm has recently emerged, offering a unified framework that adeptly addresses multiple degradation types. These innovative models enhance the convenience and versatility by adaptively learning degradation-specific features while simultaneously leveraging shared knowledge across diverse corruptions. In this survey, we provide the first in-depth and systematic overview of AiOIR, delivering a structured taxonomy that categorizes existing methods by architectural designs, learning paradigms, and their core innovations. We systematically categorize current approaches and assess the challenges these models encounter, outlining research directions to propel this rapidly evolving field. To facilitate the evaluation of existing methods, we also consolidate widely-used datasets, evaluation protocols, and implementation practices, and compare and summarize the most advanced open-source models. As the first comprehensive review dedicated to AiOIR, this paper aims to map the conceptual landscape, synthesize prevailing techniques, and ignite further exploration toward more intelligent, unified, and adaptable visual restoration systems. A curated code repository is available at https://github.com/Harbinzzy/All-in-One-Image-Restoration-Survey.
URLs: https://github.com/Harbinzzy/All-in-One-Image-Restoration-Survey.
Authors: Rui Tian, Qi Dai, Jianmin Bao, Kai Qiu, Yifan Yang, Chong Luo, Zuxuan Wu, Yu-Gang Jiang
Abstract: Commercial video generation models have exhibited realistic, high-fidelity results but are still restricted to limited access. One crucial obstacle for large-scale applications is the expensive training and inference cost. In this paper, we argue that videos contain significantly more redundant information than images, allowing them to be encoded with very few motion latents. Towards this goal, we design an image-conditioned VAE that projects videos into extremely compressed latent space and decode them based on content images. This magic Reducio charm enables 64x reduction of latents compared to a common 2D VAE, without sacrificing the quality. Building upon Reducio-VAE, we can train diffusion models for high-resolution video generation efficiently. Specifically, we adopt a two-stage generation paradigm, first generating a condition image via text-to-image generation, followed by text-image-to-video generation with the proposed Reducio-DiT. Extensive experiments show that our model achieves strong performance in evaluation. More importantly, our method significantly boosts the training and inference efficiency of video LDMs. Reducio-DiT is trained in just 3.2K A100 GPU hours in total and can generate a 16-frame 1024$\times$1024 video clip within 15.5 seconds on a single A100 GPU. Code released at https://github.com/microsoft/Reducio-VAE .
Authors: Qiao Yu, Xianzhi Li, Yuan Tang, Xu Han, Long Hu, Yixue Hao, Min Chen
Abstract: Generating 3D meshes from a single image is an important but ill-posed task. Existing methods mainly adopt 2D multiview diffusion models to generate intermediate multiview images, and use the Large Reconstruction Model (LRM) to create the final meshes. However, the multiview images exhibit local inconsistencies, and the meshes often lack fidelity to the input image or look blurry. We propose Fancy123, featuring two enhancement modules and an unprojection operation to address the above three issues, respectively. The appearance enhancement module deforms the 2D multiview images to realign misaligned pixels for better multiview consistency. The fidelity enhancement module deforms the 3D mesh to match the input image. The unprojection of the input image and deformed multiview images onto LRM's generated mesh ensures high clarity, discarding LRM's predicted blurry-looking mesh colors. Extensive qualitative and quantitative experiments verify Fancy123's SoTA performance with significant improvement. Also, the two enhancement modules are plug-and-play and work at inference time, allowing seamless integration into various existing single-image-to-3D methods. Code at: https://github.com/YuQiao0303/Fancy123
Authors: Haoyu Wang, Renshuai Tao, Wei Wang, Yunchao Wei
Abstract: Detecting prohibited items in X-ray security imagery is a challenging yet crucial task. With the rapid advancement of deep learning, object detection algorithms have been widely applied in this area. However, the distribution of object classes in real-world prohibited item detection scenarios often exhibits a distinct long-tailed distribution. Due to the unique principles of X-ray imaging, conventional methods for long-tailed object detection are often ineffective in this domain. To tackle these challenges, we introduce the Prior-Aware Debiasing Framework (PAD-F), a novel approach that employs a two-pronged strategy leveraging both material and co-occurrence priors. At the data level, our Explicit Material-Aware Augmentation (EMAA) component generates numerous challenging training samples for tail classes. It achieves this through a placement strategy guided by material-specific absorption rates and a gradient-based Poisson blending technique. At the feature level, the Implicit Co-occurrence Aggregator (ICA) acts as a plug-in module that enhances features for ambiguous objects by implicitly learning and aggregating statistical co-occurrence relationships within the image. Extensive experiments on the HiXray and PIDray datasets demonstrate that PAD-F significantly boosts the performance of multiple popular detectors. It achieves an absolute improvement of up to +17.2% in AP50 for tail classes and comprehensively outperforms existing state-of-the-art methods. Our work provides an effective and versatile solution to the critical problem of long-tailed detection in X-ray security.
Authors: Yuci Liang, Xinheng Lyu, Wenting Chen, Meidan Ding, Jipeng Zhang, Xiangjian He, Song Wu, Xiaohan Xing, Sen Yang, Xiyue Wang, Linlin Shen
Abstract: Recent advancements in computational pathology have produced patch-level Multi-modal Large Language Models (MLLMs), but these models are limited by their inability to analyze whole slide images (WSIs) comprehensively and their tendency to bypass crucial morphological features that pathologists rely on for diagnosis. To address these challenges, we first introduce WSI-Bench, a large-scale morphology-aware benchmark containing 180k VQA pairs from 9,850 WSIs across 30 cancer types, designed to evaluate MLLMs' understanding of morphological characteristics crucial for accurate diagnosis. Building upon this benchmark, we present WSI-LLaVA, a novel framework for gigapixel WSI understanding that employs a three-stage training approach: WSI-text alignment, feature space alignment, and task-specific instruction tuning. To better assess model performance in pathological contexts, we develop two specialized WSI metrics: WSI-Precision and WSI-Relevance. Experimental results demonstrate that WSI-LLaVA outperforms existing models across all capability dimensions, with a significant improvement in morphological analysis, establishing a clear correlation between morphological understanding and diagnostic accuracy.
Authors: Renlong Wu, Zhilu Zhang, Mingyang Chen, Zifei Yan, Wangmeng Zuo
Abstract: Recent 4D reconstruction methods have yielded impressive results but rely on sharp videos as supervision. However, motion blur often occurs in videos due to camera shake and object movement, while existing methods render blurry results when using such videos for reconstructing 4D models. Although a few approaches attempted to address the problem, they struggled to produce high-quality results, due to the inaccuracy in estimating continuous dynamic representations within the exposure time. Encouraged by recent works in 3D motion trajectory modeling using 3D Gaussian Splatting (3DGS), we take 3DGS as the scene representation manner, and propose Deblur4DGS to reconstruct a high-quality 4D model from blurry monocular video. Specifically, we transform continuous dynamic representations estimation within an exposure time into the exposure time estimation. Moreover, we introduce the exposure regularization term, multi-frame, and multi-resolution consistency regularization term to avoid trivial solutions. Furthermore, to better represent objects with large motion, we suggest blur-aware variable canonical Gaussians. Beyond novel-view synthesis, Deblur4DGS can be applied to improve blurry video from multiple perspectives, including deblurring, frame interpolation, and video stabilization. Extensive experiments in both synthetic and real-world data on the above four tasks show that Deblur4DGS outperforms state-of-the-art 4D reconstruction methods. The codes are available at https://github.com/ZcsrenlongZ/Deblur4DGS.
Authors: Tianwei Yin, Qiang Zhang, Richard Zhang, William T. Freeman, Fredo Durand, Eli Shechtman, Xun Huang
Abstract: Current video diffusion models achieve impressive generation quality but struggle in interactive applications due to bidirectional attention dependencies. The generation of a single frame requires the model to process the entire sequence, including the future. We address this limitation by adapting a pretrained bidirectional diffusion transformer to an autoregressive transformer that generates frames on-the-fly. To further reduce latency, we extend distribution matching distillation (DMD) to videos, distilling 50-step diffusion model into a 4-step generator. To enable stable and high-quality distillation, we introduce a student initialization scheme based on teacher's ODE trajectories, as well as an asymmetric distillation strategy that supervises a causal student model with a bidirectional teacher. This approach effectively mitigates error accumulation in autoregressive generation, allowing long-duration video synthesis despite training on short clips. Our model achieves a total score of 84.27 on the VBench-Long benchmark, surpassing all previous video generation models. It enables fast streaming generation of high-quality videos at 9.4 FPS on a single GPU thanks to KV caching. Our approach also enables streaming video-to-video translation, image-to-video, and dynamic prompting in a zero-shot manner.
Authors: Yanlai Yang, Mengye Ren
Abstract: Self-supervised learning holds the promise of learning good representations from real-world continuous uncurated data streams. However, most existing works in visual self-supervised learning focus on static images or artificial data streams. Towards exploring a more realistic learning substrate, we investigate streaming self-supervised learning from long-form real-world egocentric video streams. Inspired by the event segmentation mechanism in human perception and memory, we propose "Memory Storyboard" that groups recent past frames into temporal segments for more effective summarization of the past visual streams for memory replay. To accommodate efficient temporal segmentation, we propose a two-tier memory hierarchy: the recent past is stored in a short-term memory, and the storyboard temporal segments are then transferred to a long-term memory. Experiments on real-world egocentric video datasets including SAYCam and KrishnaCam show that contrastive learning objectives on top of storyboard frames result in semantically meaningful representations that outperform those produced by state-of-the-art unsupervised continual learning methods.
Authors: He Zhang, Xinyi Fu
Abstract: This study investigates the feasibility and performance of using large multimodal models (LMMs) to automatically annotate human emotions in everyday scenarios. We conducted experiments on the DailyLife subset of the publicly available FERV39k dataset, employing the GPT-4o-mini model for rapid, zero-shot labeling of key frames extracted from video segments. Under a seven-class emotion taxonomy ("Angry," "Disgust," "Fear," "Happy," "Neutral," "Sad," "Surprise"), the LMM achieved an average precision of approximately 50%. In contrast, when limited to ternary emotion classification (negative/neutral/positive), the average precision increased to approximately 64%. Additionally, we explored a strategy that integrates multiple frames within 1-2 second video clips to enhance labeling performance and reduce costs. The results indicate that this approach can slightly improve annotation accuracy. Overall, our preliminary findings highlight the potential application of zero-shot LMMs in human facial emotion annotation tasks, offering new avenues for reducing labeling costs and broadening the applicability of LMMs in complex multimodal environments.
Authors: Victor Shea-Jay Huang, Le Zhuo, Yi Xin, Zhaokai Wang, Fu-Yun Wang, Yuchi Wang, Renrui Zhang, Peng Gao, Hongsheng Li
Abstract: Diffusion Transformers (DiTs) are a powerful yet underexplored class of generative models compared to U-Net-based diffusion architectures. We propose TIDE-Temporal-aware sparse autoencoders for Interpretable Diffusion transformErs-a framework designed to extract sparse, interpretable activation features across timesteps in DiTs. TIDE effectively captures temporally-varying representations and reveals that DiTs naturally learn hierarchical semantics (e.g., 3D structure, object class, and fine-grained concepts) during large-scale pretraining. Experiments show that TIDE enhances interpretability and controllability while maintaining reasonable generation quality, enabling applications such as safe image editing and style transfer.
Authors: Haoran Chen, Ping Wang, Zihan Zhou, Xu Zhang, Zuxuan Wu, Yu-Gang Jiang
Abstract: Class-incremental learning (CIL) enables models to learn new classes progressively while preserving knowledge of previously learned ones. Recent advances in this field have shifted towards parameter-efficient fine-tuning techniques, with many approaches building upon the framework that maintains a pool of learnable prompts. Although effective, these methods introduce substantial computational overhead, primarily due to prompt pool querying and increased input sequence lengths from prompt concatenation. In this work, we present a novel prompt-based approach that addresses this limitation. Our method trains a single set of shared prompts across all tasks and, rather than concatenating prompts to the input, directly modifies the CLS token's attention computation by adding the prompts to it. This simple and lightweight design not only significantly reduces computational complexity-both in terms of inference costs and the number of trainable parameters-but also eliminates the need to optimize prompt lengths for different downstream tasks, offering a more efficient yet powerful solution for rehearsal-free class-incremental learning. Extensive experiments across a diverse range of CIL benchmarks demonstrate the effectiveness of our approach, highlighting its potential to establish a new prompt-based CIL paradigm. Furthermore, experiments on general recognition benchmarks beyond the CIL setting also show strong performance, positioning our method as a promising candidate for a general parameter-efficient fine-tuning approach.
Authors: Maxim Popov, Regina Kurkova, Mikhail Iumanov, Jaafar Mahmoud, Sergey Kolyubin
Abstract: Open Semantic Mapping (OSM) is a key technology in robotic perception, combining semantic segmentation and SLAM techniques. This paper introduces a dynamically configurable and highly automated LLM/LVLM-powered pipeline for evaluating OSM solutions called OSMa-Bench (Open Semantic Mapping Benchmark). The study focuses on evaluating state-of-the-art semantic mapping algorithms under varying indoor lighting conditions, a critical challenge in indoor environments. We introduce a novel dataset with simulated RGB-D sequences and ground truth 3D reconstructions, facilitating the rigorous analysis of mapping performance across different lighting conditions. Through experiments on leading models such as ConceptGraphs, BBQ and OpenScene, we evaluate the semantic fidelity of object recognition and segmentation. Additionally, we introduce a Scene Graph evaluation method to analyze the ability of models to interpret semantic structure. The results provide insights into the robustness of these models, forming future research directions for developing resilient and adaptable robotic systems. Project page is available at https://be2rlab.github.io/OSMa-Bench/.
Authors: Yuanze Li, Shihao Yuan, Haolin Wang, Qizhang Li, Ming Liu, Chen Xu, Guangming Shi, Wangmeng Zuo
Abstract: Although recent methods have tried to introduce large multimodal models (LMMs) into industrial anomaly detection (IAD), their generalization in the IAD field is far inferior to that for general purposes. We summarize the main reasons for this gap into two aspects. On one hand, general-purpose LMMs lack cognition of defects in the visual modality, thereby failing to sufficiently focus on defect areas. Therefore, we propose to modify the AnyRes structure of the LLaVA model, providing the potential anomalous areas identified by existing IAD models to the LMMs. On the other hand, existing methods mainly focus on identifying defects by learning defect patterns or comparing with normal samples, yet they fall short of understanding the causes of these defects. Considering that the generation of defects is closely related to the manufacturing process, we propose a manufacturing-driven IAD paradigm. An instruction-tuning dataset for IAD (InstructIAD) and a data organization approach for Chain-of-Thought with manufacturing (CoT-M) are designed to leverage the manufacturing process for IAD. Based on the above two modifications, we present Triad, a novel LMM-based method incorporating an expert-guided region-of-interest tokenizer and manufacturing process for industrial anomaly detection. Extensive experiments show that our Triad not only demonstrates competitive performance against current LMMs but also achieves further improved accuracy when equipped with manufacturing processes. Source code, training data, and pre-trained models will be publicly available at https://github.com/tzjtatata/Triad.
Authors: Haiyang Ying, Matthias Zwicker
Abstract: Edges are one of the most basic parametric primitives to describe structural information in 3D. In this paper, we study parametric 3D edge reconstruction from calibrated multi-view images. Previous methods usually reconstruct a 3D edge point set from multi-view 2D edge images, and then fit 3D edges to the point set. However, noise in the point set may cause gaps among fitted edges, and the recovered edges may not align with input multi-view images since the edge fitting depends only on the reconstructed 3D point set. To mitigate these problems, we propose SketchSplat, a method to reconstruct accurate, complete, and compact 3D edges via differentiable multi-view sketch splatting. We represent 3D edges as sketches, which are parametric lines and curves defined by attributes including control points, scales, and opacity. During reconstruction, we iteratively sample Gaussian points from a set of sketches and rasterize the Gaussians onto 2D edge images. Then the gradient of the image loss can be back-propagated to optimize the sketch attributes. Our method bridges 2D edge images and 3D edges in a differentiable manner, which ensures that 3D edges align well with 2D images and leads to accurate and complete results. We also propose a series of adaptive topological operations to reduce redundant edges and apply them along with the sketch optimization, yielding a more compact reconstruction. Finally, we contribute an accurate 2D edge detector that improves the performance of both ours and existing methods. Experiments show that our method achieves state-of-the-art accuracy, completeness, and compactness on a benchmark CAD dataset.
Authors: Hussain Md. Safwan, Mahbub Islam Mahim
Abstract: A common dilemma while photographing a scene is whether to capture it at a wider angle, allowing more of the scene to be covered but in less detail or to click in a narrow angle that captures better details but leaves out portions of the scene. We propose a novel method in this paper that infuses wider shots with finer quality details that is usually associated with an image captured by the primary lens by capturing the same scene using both narrow and wide field of view (FoV) lenses. We do so by training a Generative Adversarial Network (GAN)-based model to learn to extract the visual quality parameters from a narrow-angle shot and to transfer these to the corresponding wide-angle image of the scene using residual connections and an attention-based fusion module. We have mentioned in details the proposed technique to isolate the visual essence of an image and to transfer it into another image. We have also elaborately discussed our implementation details and have presented the results of evaluation over several benchmark datasets and comparisons with contemporary advancements in the field.
Authors: Nikolai R\"ohrich, Alwin Hoffmann, Richard Nordsieck, Emilio Zarbali, Alireza Javanmardi
Abstract: While transformers have surpassed convolutional neural networks (CNNs) in various computer vision tasks, microelectronics defect detection still largely relies on CNNs. We hypothesize that this gap is due to the fact that a) transformers have an increased need for data and b) (labelled) image generation procedures for microelectronics are costly, and data is therefore sparse. Whereas in other domains, pre-training on large natural image datasets can mitigate this problem, in microelectronics transfer learning is hindered due to the dissimilarity of domain data and natural images. We address this challenge through self pre-training, where models are pre-trained directly on the target dataset, rather than another dataset. We propose a resource-efficient vision transformer (ViT) pre-training framework for defect detection in microelectronics based on masked autoencoders (MAE). We perform pre-training and defect detection using a dataset of less than 10,000 scanning acoustic microscopy (SAM) images. Our experimental results show that our approach leads to substantial performance gains compared to a) supervised ViT, b) ViT pre-trained on natural image datasets, and c) state-of-the-art CNN-based defect detection models used in microelectronics. Additionally, interpretability analysis reveals that our self pre-trained models attend to defect-relevant features such as cracks in the solder material, while baseline models often attend to spurious patterns. This shows that our approach yields defect-specific feature representations, resulting in more interpretable and generalizable transformer models for this data-sparse domain.
Authors: Yucheng Lu, Shunxin Wang, Dovile Juodelyte, Veronika Cheplygina
Abstract: In this paper, we explore how conventional image enhancement can improve model robustness in medical image analysis. By applying commonly used normalization methods to images from various vendors and studying their influence on model generalization in transfer learning, we show that the nonlinear characteristics of domain-specific image dynamics cannot be addressed by simple linear transforms. To tackle this issue, we reformulate the image harmonization task as an exposure correction problem and propose a method termed Global Deep Curve Estimation (GDCE) to reduce domain-specific exposure mismatch. GDCE performs enhancement via a pre-defined polynomial function and is trained with a "domain discriminator", aiming to improve model transparency in downstream tasks compared to existing black-box methods.
Authors: Jeremy Klotz, Shree K. Nayar
Abstract: A solar panel harvests the most energy when pointing in the direction that maximizes the total illumination (irradiance) falling on it. Given an arbitrary panel orientation and an arbitrary environmental illumination, we address the problem of finding the direction of maximum total irradiance. We develop a minimal sensing approach where measurements from just four photodetectors are used to iteratively vary the tilt of the panel to maximize the irradiance. Many environments produce irradiance functions with multiple local maxima. As a result, simply measuring the gradient of the irradiance function and applying gradient ascent will not work. We show that a larger, optimized tilt between the detectors and the panel is equivalent to blurring the irradiance function. This has the effect of eliminating local maxima and turning the irradiance function into a unimodal one, whose maximum can be found using gradient ascent. We show that there is a close relationship between our approach and scale space theory. We collected a large dataset of high-dynamic range lighting environments in Manhattan, called UrbanSky. We use this dataset to conduct simulations to verify the robustness of our approach. Next, we simulate the energy harvested using our approach under dynamic illumination. Finally, we built a portable solar panel with four compact detectors and an actuator to conduct experiments in various real-world settings: direct sunlight, cloudy sky, urban settings with occlusions and shadows, and complex indoor lighting. In all cases, we show improvements in harvested energy compared to standard approaches for orienting a solar panel.
Authors: Elior Benarous, Yilun Du, Heng Yang
Abstract: This paper presents SPIE: a novel approach for semantic and structural post-training of instruction-based image editing diffusion models, addressing key challenges in alignment with user prompts and consistency with input images. We introduce an online reinforcement learning framework that aligns the diffusion model with human preferences without relying on extensive human annotations or curating a large dataset. Our method significantly improves the alignment with instructions and realism in two ways. First, SPIE captures fine nuances in the desired edit by leveraging a visual prompt, enabling detailed control over visual edits without lengthy textual prompts. Second, it achieves precise and structurally coherent modifications in complex scenes while maintaining high fidelity in instruction-irrelevant areas. This approach simplifies users' efforts to achieve highly specific edits, requiring only 5 reference images depicting a certain concept for training. Experimental results demonstrate that SPIE can perform intricate edits in complex scenes, after just 10 training steps. Finally, we showcase the versatility of our method by applying it to robotics, where targeted image edits enhance the visual realism of simulated environments, which improves their utility as proxy for real-world settings.
Authors: Songsong Xiong, Hamidreza Kasaei
Abstract: In human-centered environments such as restaurants, homes, and warehouses, robots often face challenges in accurately recognizing 3D objects. These challenges stem from the complexity and variability of these environments, including diverse object shapes. In this paper, we propose a novel Lightweight Multi-modal Multi-view Convolutional-Vision Transformer network (LM-MCVT) to enhance 3D object recognition in robotic applications. Our approach leverages the Globally Entropy-based Embeddings Fusion (GEEF) method to integrate multi-views efficiently. The LM-MCVT architecture incorporates pre- and mid-level convolutional encoders and local and global transformers to enhance feature extraction and recognition accuracy. We evaluate our method on the synthetic ModelNet40 dataset and achieve a recognition accuracy of 95.6% using a four-view setup, surpassing existing state-of-the-art methods. To further validate its effectiveness, we conduct 5-fold cross-validation on the real-world OmniObject3D dataset using the same configuration. Results consistently show superior performance, demonstrating the method's robustness in 3D object recognition across synthetic and real-world 3D data.
Authors: Mengqi Lei, Yihong Wu, Siqi Li, Xinhu Zheng, Juan Wang, Yue Gao, Shaoyi Du
Abstract: Visual recognition relies on understanding both the semantics of image tokens and the complex interactions among them. Mainstream self-attention methods, while effective at modeling global pair-wise relations, fail to capture high-order associations inherent in real-world scenes and often suffer from redundant computation. Hypergraphs extend conventional graphs by modeling high-order interactions and offer a promising framework for addressing these limitations. However, existing hypergraph neural networks typically rely on static and hard hyperedge assignments, leading to excessive and redundant hyperedges with hard binary vertex memberships that overlook the continuity of visual semantics. To overcome these issues, we present Soft Hypergraph Neural Networks (SoftHGNNs), which extend the methodology of hypergraph computation, to make it truly efficient and versatile in visual recognition tasks. Our framework introduces the concept of soft hyperedges, where each vertex is associated with hyperedges via continuous participation weights rather than hard binary assignments. This dynamic and differentiable association is achieved by using the learnable hyperedge prototype. Through similarity measurements between token features and the prototype, the model generates semantically rich soft hyperedges. SoftHGNN then aggregates messages over soft hyperedges to capture high-order semantics. To further enhance efficiency when scaling up the number of soft hyperedges, we incorporate a sparse hyperedge selection mechanism that activates only the top-k important hyperedges, along with a load-balancing regularizer to ensure balanced hyperedge utilization. Experimental results across three tasks on five datasets demonstrate that SoftHGNN efficiently captures high-order associations in visual scenes, achieving significant performance improvements.
Authors: Mehrdad Fazli, Bowen Wei, Ahmet Sari, Ziwei Zhu
Abstract: Large vision-language models (LVLMs) achieve impressive performance on multimodal tasks but often suffer from hallucination, and confidently describe objects or attributes not present in the image. Current training-free interventions struggle to maintain accuracy in open-ended and long-form generation scenarios. We introduce the Confidence-Aware Attention Calibration (CAAC) framework to address this challenge by targeting two key biases: spatial perception bias, which distributes attention disproportionately across image tokens, and modality bias, which shifts focus from visual to textual inputs over time. CAAC employs a two-step approach: Visual-Token Calibration (VTC) to balance attention across visual tokens, and Adaptive Attention Re-Scaling (AAR) to reinforce visual grounding guided by the model's confidence. This confidence-driven adjustment ensures consistent visual alignment during generation. Experiments on CHAIR, AMBER, and POPE benchmarks demonstrate that CAAC outperforms baselines, particularly in long-form generations, effectively reducing hallucination.
Authors: Cailin Zhuang, Ailin Huang, Wei Cheng, Jingwei Wu, Yaoqi Hu, Jiaqi Liao, Hongyuan Wang, Xinyao Liao, Weiwei Cai, Hengyuan Xu, Xuanyang Zhang, Xianfang Zeng, Zhewei Huang, Gang Yu, Chi Zhang
Abstract: Story visualization aims to generate coherent image sequences that faithfully depict a narrative and align with character references. Despite progress in generative models, existing benchmarks are narrow in scope, often limited to short prompts, no character reference, or single-image cases, and fall short of real-world storytelling complexity. This hinders a nuanced understanding of model capabilities and limitations. We present ViStoryBench, a comprehensive benchmark designed to evaluate story visualization models across diverse narrative structures, visual styles, and character settings. The benchmark features richly annotated multi-shot scripts derived from curated stories spanning literature, film, and folklore. Large language models assist in story summarization and script generation, with all outputs verified by humans to ensure coherence and fidelity. Character references are carefully curated to maintain intra-story consistency across varying artistic styles. To enable thorough evaluation, ViStoryBench introduces a set of automated metrics that assess character consistency, style similarity, prompt adherence, aesthetic quality, and generation artifacts such as copy-paste behavior. These metrics are validated through human studies, and used to benchmark a broad range of open-source and commercial models. ViStoryBench offers a high-fidelity, multi-dimensional evaluation suite that facilitates systematic analysis and fosters future progress in visual storytelling.
Authors: Jiwen Yu, Jianhong Bai, Yiran Qin, Quande Liu, Xintao Wang, Pengfei Wan, Di Zhang, Xihui Liu
Abstract: Recent advances in interactive video generation have shown promising results, yet existing approaches struggle with scene-consistent memory capabilities in long video generation due to limited use of historical context. In this work, we propose Context-as-Memory, which utilizes historical context as memory for video generation. It includes two simple yet effective designs: (1) storing context in frame format without additional post-processing; (2) conditioning by concatenating context and frames to be predicted along the frame dimension at the input, requiring no external control modules. Furthermore, considering the enormous computational overhead of incorporating all historical context, we propose the Memory Retrieval module to select truly relevant context frames by determining FOV (Field of View) overlap between camera poses, which significantly reduces the number of candidate frames without substantial information loss. Experiments demonstrate that Context-as-Memory achieves superior memory capabilities in interactive long video generation compared to SOTAs, even generalizing effectively to open-domain scenarios not seen during training. The link of our project page is https://context-as-memory.github.io/.
Authors: Debarshi Brahma, Soma Biswas
Abstract: Foundation Vision-Language Models (VLMs) like CLIP exhibit strong generalization capabilities due to large-scale pretraining on diverse image-text pairs. However, their performance often degrades when applied to target datasets with significant distribution shifts in both visual appearance and class semantics. Recent few-shot learning approaches adapt CLIP to downstream tasks using limited labeled data via adapter or prompt tuning, but are not specifically designed to handle such extreme domain shifts. Conversely, some works addressing cross-domain few-shot learning consider such domain-shifted scenarios but operate in an episodic setting with only a few classes per episode, limiting their applicability to real-world deployment, where all classes must be handled simultaneously. To address this gap, we propose a novel framework, MIST (Multiple Stochastic Prompt Tuning), for efficiently adapting CLIP to datasets with extreme distribution shifts using only a few labeled examples, in scenarios involving all classes at once. Specifically, we introduce multiple learnable prompts per class to effectively capture diverse modes in visual representations arising from distribution shifts. To further enhance generalization, these prompts are modeled as learnable Gaussian distributions, enabling efficient exploration of the prompt parameter space and reducing overfitting caused by limited supervision. Extensive experiments and comparisons with state-of-the-art methods demonstrate the effectiveness of the proposed framework.
Authors: Suhan Woo, Seongwon Lee, Jinwoo Jang, Euntai Kim
Abstract: When applying Visual Place Recognition (VPR) to real-world mobile robots and similar applications, perspective-to-equirectangular (P2E) formulation naturally emerges as a suitable approach to accommodate diverse query images captured from various viewpoints. In this paper, we introduce HypeVPR, a novel hierarchical embedding framework in hyperbolic space, designed to address the unique challenges of P2E VPR. The key idea behind HypeVPR is that visual environments captured by panoramic views exhibit inherent hierarchical structures. To leverage this property, we employ hyperbolic space to represent hierarchical feature relationships and preserve distance properties within the feature space. To achieve this, we propose a hierarchical feature aggregation mechanism that organizes local-to-global feature representations within hyperbolic space. Additionally, HypeVPR adopts an efficient coarse-to-fine search strategy to enable flexible control over accuracy-efficiency trade-offs and ensure robust matching even between descriptors from different image types. This approach allows HypeVPR to outperform existing methods while significantly accelerating retrieval and reducing database storage requirements. The code and models will be released at https://github.com/suhan-woo/HypeVPR.git.
Authors: Bimal Kumar Ray
Abstract: Many studies have been conducted to solve the problem of approximating a digital boundary by piece straight-line segments for the further processing required in computer vision applications. The authors of these studies compared their schemes to determine the best one. The initial measure used to assess the goodness of fit of a polygonal approximation was the figure of merit. Later,it was noted that this measure was not an appropriate metric for a valid reason which is why Rosin-through mathematical analysis-introduced a measure called merit. However,this measure involves an optimal scheme of polygonal approximation,so it is time-consuming to compute it to assess the goodness of fit of an approximation. This led many researchers to use a weighted figure of merit as a substitute for Rosin's measure to compare sub optimal schemes. An attempt is made in this communication to investigate whether the two measures-weighted figure of merit and Rosin's measure-are related so that one can be used instead of the other, and toward this end, theoretical analysis, experimental investigation and statistical analysis are carried out. The mathematical formulas for the weighted figure of merit and Rosin's measure are analyzed, and through proof of theorems,it is found that the two measures are theoretically independent of each other. The graphical analysis of experiments carried out using a public dataset supports the results of the theoretical analysis. The statistical analysis via Pearson's correlation coefficient and non-linear correlation measure also revealed that the two measures are uncorrelated. This analysis leads one to conclude that if a suboptimal scheme is found to be better (worse) than some other suboptimal scheme,as indicated by Rosin's measure,then the same conclusion cannot be drawn using a weighted figure of merit,so one cannot use a weighted figure of merit instead of Rosin's measure.
Authors: Shravan Nayak, Mehar Bhatia, Xiaofeng Zhang, Verena Rieser, Lisa Anne Hendricks, Sjoerd van Steenkiste, Yash Goyal, Karolina Sta\'nczak, Aishwarya Agrawal
Abstract: The increasing ubiquity of text-to-image (T2I) models as tools for visual content generation raises concerns about their ability to accurately represent diverse cultural contexts -- where missed cues can stereotype communities and undermine usability. In this work, we present the first study to systematically quantify the alignment of T2I models and evaluation metrics with respect to both explicit (stated) as well as implicit (unstated, implied by the prompt's cultural context) cultural expectations. To this end, we introduce CulturalFrames, a novel benchmark designed for rigorous human evaluation of cultural representation in visual generations. Spanning 10 countries and 5 socio-cultural domains, CulturalFrames comprises 983 prompts, 3637 corresponding images generated by 4 state-of-the-art T2I models, and over 10k detailed human annotations. We find that across models and countries, cultural expectations are missed an average of 44% of the time. Among these failures, explicit expectations are missed at a surprisingly high average rate of 68%, while implicit expectation failures are also significant, averaging 49%. Furthermore, we show that existing T2I evaluation metrics correlate poorly with human judgments of cultural alignment, irrespective of their internal reasoning. Collectively, our findings expose critical gaps, provide a concrete testbed, and outline actionable directions for developing culturally informed T2I models and metrics that improve global usability.
Authors: Yang Yao, Lingyu Li, Jiaxin Song, Chiyu Chen, Zhenqi He, Yixu Wang, Xin Wang, Tianle Gu, Jie Li, Yan Teng, Yingchun Wang
Abstract: As Multimodal Large Language Models (MLLMs) continue to evolve, their cognitive and reasoning capabilities have seen remarkable progress. However, challenges in visual fine-grained perception and commonsense causal inference persist. This paper introduces Argus Inspection, a multimodal benchmark with two levels of difficulty, emphasizing detailed visual recognition while incorporating real-world commonsense understanding to evaluate causal reasoning abilities. Expanding on it, we present the Eye of Panoptes framework, which integrates a binary parametric Sigmoid metric with an indicator function, enabling a more holistic evaluation of MLLMs' responses in opinion-based reasoning tasks. Experiments conducted on 26 mainstream MLLMs reveal that the highest performance in visual fine-grained reasoning reaches only 0.46, highlighting considerable potential for enhancement. Our research offers valuable perspectives for the continued refinement of MLLMs.
Authors: Langyu Wang, Bingke Zhu, Yingying Chen, Yiyuan Zhang, Ming Tang, Jinqiao Wang
Abstract: The weakly-supervised audio-visual video parsing (AVVP) aims to predict all modality-specific events and locate their temporal boundaries. Despite significant progress, due to the limitations of the weakly-supervised and the deficiencies of the model architecture, existing methods are lacking in simultaneously improving both the segment-level prediction and the event-level prediction. In this work, we propose a audio-visual Mamba network with pseudo labeling aUGmentation (MUG) for emphasising the uniqueness of each segment and excluding the noise interference from the alternate modalities. Specifically, we annotate some of the pseudo-labels based on previous work. Using unimodal pseudo-labels, we perform cross-modal random combinations to generate new data, which can enhance the model's ability to parse various segment-level event combinations. For feature processing and interaction, we employ a audio-visual mamba network. The AV-Mamba enhances the ability to perceive different segments and excludes additional modal noise while sharing similar modal information. Our extensive experiments demonstrate that MUG improves state-of-the-art results on LLP dataset in all metrics (e.g,, gains of 2.1% and 1.2% in terms of visual Segment-level and audio Segment-level metrics). Our code is available at https://github.com/WangLY136/MUG.
Authors: Junjie Wang, Yunhan Tang, Yijie Wang, Zhihao Yuan, Huan Wang, Yangfan He, Bin Li
Abstract: Multimodal Large Language Models (MLLMs) have pushed the frontiers of Knowledge-Based Visual Question Answering (KBVQA), yet their reasoning is fundamentally bottlenecked by a reliance on uni-dimensional evidence. This "seeing only the trees, but not the forest" approach prevents robust, multi-faceted understanding. Inspired by the principle of seeing both the forest and trees, we propose Synergos-VQA, a novel synergistic reasoning framework. At its core, Synergos-VQA concurrently generates and fuses three complementary evidence streams at inference time: (1) Holistic Evidence to perceive the entire scene (the "forest"), (2) Structural Evidence from a prototype-driven module to identify key objects (the "trees"), and (3) Causal Evidence from a counterfactual probe to ensure the reasoning is robustly grounded. By synergistically fusing this multi-faceted evidence, our framework achieves a more comprehensive and reliable reasoning process. Extensive experiments show that Synergos-VQA decisively establishes a new state-of-the-art on three challenging benchmarks, including OK-VQA and A-OKVQA. Furthermore, our approach demonstrates strong plug-and-play capabilities, significantly boosting various open-source MLLMs and proving that superior methodological design can outperform sheer model scale.
Authors: Yongsong Huang, Tomo Miyazaki, Xiaofeng Liu, Shinichiro Omachi
Abstract: Infrared Image Super-Resolution (IRSR) is challenged by the low contrast and sparse textures of infrared data, requiring robust long-range modeling to maintain global coherence. While State-Space Models like Mamba offer proficiency in modeling long-range dependencies for this task, their inherent 1D causal scanning mechanism fragments the global context of 2D images, hindering fine-detail restoration. To address this, we propose Global Phase and Spectral Prompt-guided Mamba (GPSMamba), a framework that synergizes architectural guidance with non-causal supervision. First, our Adaptive Semantic-Frequency State Space Module (ASF-SSM) injects a fused semantic-frequency prompt directly into the Mamba block, integrating non-local context to guide reconstruction. Then, a novel Thermal-Spectral Attention and Phase Consistency Loss provides explicit, non-causal supervision to enforce global structural and spectral fidelity. By combining these two innovations, our work presents a systematic strategy to mitigate the limitations of causal modeling. Extensive experiments demonstrate that GPSMamba achieves state-of-the-art performance, validating our approach as a powerful new paradigm for infrared image restoration. Code is available at https://github.com/yongsongH/GPSMamba.
Authors: Liang Yao, Fan Liu, Hongbo Lu, Chuanyi Zhang, Rui Min, Shengxiang Xu, Shimin Di, Pai Peng
Abstract: Remote sensing imagery presents vast, inherently unstructured spatial data, necessitating sophisticated reasoning to interpret complex user intents and contextual relationships beyond simple recognition tasks. In this paper, we aim to construct an Earth observation workflow to handle complex queries by reasoning about spatial context and user intent. As a reasoning workflow, it should autonomously explore and construct its own inference paths, rather than being confined to predefined ground-truth sequences. Ideally, its architecture ought to be unified yet generalized, possessing capabilities to perform diverse reasoning tasks through one model without requiring additional fine-tuning. Existing remote sensing approaches rely on supervised fine-tuning paradigms and task-specific heads, limiting both autonomous reasoning and unified generalization. To this end, we propose RemoteReasoner, a unified workflow for geospatial reasoning. The design of RemoteReasoner integrates a multi-modal large language model (MLLM) for interpreting user instructions and localizing targets, together with task transformation strategies that enable multi-granularity tasks, including object-, region-, and pixel-level. In contrast to existing methods, our framework is trained with reinforcement learning (RL) to endow the MLLM sufficient reasoning autonomy. At the inference stage, our transformation strategies enable diverse task output formats without requiring task-specific decoders or further fine-tuning. Experiments demonstrated that RemoteReasoner achieves state-of-the-art (SOTA) performance across multi-granularity reasoning tasks. Furthermore, it retains the MLLM's inherent generalization capability, demonstrating robust performance on unseen tasks and out-of-distribution categories.
Authors: Rishav Kumar, D. Santhosh Reddy, P. Rajalakshmi
Abstract: We introduce DriveIndia, a large-scale object detection dataset purpose-built to capture the complexity and unpredictability of Indian traffic environments. The dataset contains 66,986 high-resolution images annotated in YOLO format across 24 traffic-relevant object categories, encompassing diverse conditions such as varied weather (fog, rain), illumination changes, heterogeneous road infrastructure, and dense, mixed traffic patterns and collected over 120+ hours and covering 3,400+ kilometers across urban, rural, and highway routes. DriveIndia offers a comprehensive benchmark for real-world autonomous driving challenges. We provide baseline results using state-of-the-art YOLO family models, with the top-performing variant achieving a mAP50 of 78.7%. Designed to support research in robust, generalizable object detection under uncertain road conditions, DriveIndia will be publicly available via the TiHAN-IIT Hyderabad dataset repository https://tihan.iith.ac.in/TiAND.html (Terrestrial Datasets -> Camera Dataset).
Authors: Jordan Vice, Naveed Akhtar, Yansong Gao, Richard Hartley, Ajmal Mian
Abstract: Vision-Language Models (VLMs) are increasingly used as perceptual modules for visual content reasoning, including through captioning and DeepFake detection. In this work, we expose a critical vulnerability of VLMs when exposed to subtle, structured perturbations in the frequency domain. Specifically, we highlight how these feature transformations undermine authenticity/DeepFake detection and automated image captioning tasks. We design targeted image transformations, operating in the frequency domain to systematically adjust VLM outputs when exposed to frequency-perturbed real and synthetic images. We demonstrate that the perturbation injection method generalizes across five state-of-the-art VLMs which includes different-parameter Qwen2/2.5 and BLIP models. Experimenting across ten real and generated image datasets reveals that VLM judgments are sensitive to frequency-based cues and may not wholly align with semantic content. Crucially, we show that visually-imperceptible spatial frequency transformations expose the fragility of VLMs deployed for automated image captioning and authenticity detection tasks. Our findings under realistic, black-box constraints challenge the reliability of VLMs, underscoring the need for robust multimodal perception systems.
Authors: Li Siyao, Yao Feng, Omid Taheri, Chen Change Loy, Michael J. Black
Abstract: While current general-purpose 3D human models (e.g., SMPL-X) efficiently represent accurate human shape and pose, they lacks the ability to physically interact with the environment due to the kinematic nature. As a result, kinematic-based interaction models often suffer from issues such as interpenetration and unrealistic object dynamics. To address this limitation, we introduce a novel approach that embeds SMPL-X into a tangible entity capable of dynamic physical interactions with its surroundings. Specifically, we propose a "half-physics" mechanism that transforms 3D kinematic motion into a physics simulation. Our approach maintains kinematic control over inherent SMPL-X poses while ensuring physically plausible interactions with scenes and objects, effectively eliminating penetration and unrealistic object dynamics. Unlike reinforcement learning-based methods, which demand extensive and complex training, our half-physics method is learning-free and generalizes to any body shape and motion; meanwhile, it operates in real time. Moreover, it preserves the fidelity of the original kinematic motion while seamlessly integrating physical interactions
Authors: Stefan Englmeier, Max A. B\"uttner, Katharina Winter, Fabian B. Flohr
Abstract: Autonomous driving systems must operate reliably in safety-critical scenarios, particularly those involving unusual or complex behavior by Vulnerable Road Users (VRUs). Identifying these edge cases in driving datasets is essential for robust evaluation and generalization, but retrieving such rare human behavior scenarios within the long tail of large-scale datasets is challenging. To support targeted evaluation of autonomous driving systems in diverse, human-centered scenarios, we propose a novel context-aware motion retrieval framework. Our method combines Skinned Multi-Person Linear (SMPL)-based motion sequences and corresponding video frames before encoding them into a shared multimodal embedding space aligned with natural language. Our approach enables the scalable retrieval of human behavior and their context through text queries. This work also introduces our dataset WayMoCo, an extension of the Waymo Open Dataset. It contains automatically labeled motion and scene context descriptions derived from generated pseudo-ground-truth SMPL sequences and corresponding image data. Our approach outperforms state-of-the-art models by up to 27.5% accuracy in motion-context retrieval, when evaluated on the WayMoCo dataset.
Authors: Kagan Ozturk, Deeksha Arun, Kevin W. Bowyer, Patrick Flynn
Abstract: Ear recognition has gained attention as a reliable biometric technique due to the distinctive characteristics of human ears. With the increasing availability of large-scale datasets, convolutional neural networks (CNNs) have been widely adopted to learn features directly from raw ear images, outperforming traditional hand-crafted methods. However, the effect of bilateral ear symmetry on the features learned by CNNs has received little attention in recent studies. In this paper, we investigate how bilateral ear symmetry influences the effectiveness of CNN-based ear recognition. To this end, we first develop an ear side classifier to automatically categorize ear images as either left or right. We then explore the impact of incorporating this side information during both training and test. Cross-dataset evaluations are conducted on five datasets. Our results suggest that treating left and right ears separately during training and testing can lead to notable performance improvements. Furthermore, our ablation studies on alignment strategies, input sizes, and various hyperparameter settings provide practical insights into training CNN-based ear recognition systems on large-scale datasets to achieve higher verification rates.
Authors: Jian Wang, Chaokang Jiang, Haitao Xu
Abstract: Diffusion-based models are redefining the state-of-the-art in end-to-end autonomous driving, yet their performance is increasingly hampered by a reliance on transformer-based fusion. These architectures face fundamental limitations: quadratic computational complexity restricts the use of high-resolution features, and a lack of spatial priors prevents them from effectively modeling the inherent structure of Bird's Eye View (BEV) representations. This paper introduces GMF-Drive (Gated Mamba Fusion for Driving), an end-to-end framework that overcomes these challenges through two principled innovations. First, we supersede the information-limited histogram-based LiDAR representation with a geometrically-augmented pillar format encoding shape descriptors and statistical features, preserving critical 3D geometric details. Second, we propose a novel hierarchical gated mamba fusion (GM-Fusion) architecture that substitutes an expensive transformer with a highly efficient, spatially-aware state-space model (SSM). Our core BEV-SSM leverages directional sequencing and adaptive fusion mechanisms to capture long-range dependencies with linear complexity, while explicitly respecting the unique spatial properties of the driving scene. Extensive experiments on the challenging NAVSIM benchmark demonstrate that GMF-Drive achieves a new state-of-the-art performance, significantly outperforming DiffusionDrive. Comprehensive ablation studies validate the efficacy of each component, demonstrating that task-specific SSMs can surpass a general-purpose transformer in both performance and efficiency for autonomous driving.
Authors: Hongbo Ma, Fei Shen, Hongbin Xu, Xiaoce Wang, Gang Xu, Jinkai Zheng, Liangqiong Qu, Ming Li
Abstract: The advancement of intelligent agents has revolutionized problem-solving across diverse domains, yet solutions for personalized fashion styling remain underexplored, which holds immense promise for promoting shopping experiences. In this work, we present StyleTailor, the first collaborative agent framework that seamlessly unifies personalized apparel design, shopping recommendation, virtual try-on, and systematic evaluation into a cohesive workflow. To this end, StyleTailor pioneers an iterative visual refinement paradigm driven by multi-level negative feedback, enabling adaptive and precise user alignment. Specifically, our framework features two core agents, i.e., Designer for personalized garment selection and Consultant for virtual try-on, whose outputs are progressively refined via hierarchical vision-language model feedback spanning individual items, complete outfits, and try-on efficacy. Counterexamples are aggregated into negative prompts, forming a closed-loop mechanism that enhances recommendation quality. To assess the performance, we introduce a comprehensive evaluation suite encompassing style consistency, visual quality, face similarity, and artistic appraisal. Extensive experiments demonstrate StyleTailor's superior performance in delivering personalized designs and recommendations, outperforming strong baselines without negative feedback and establishing a new benchmark for intelligent fashion systems.
Authors: Qiwei Tian, Chenhao Lin, Zhengyu Zhao, Qian Li, Shuai Liu, Chao Shen
Abstract: Thanks to the development of cross-modal models, text-to-video retrieval (T2VR) is advancing rapidly, but its robustness remains largely unexamined. Existing attacks against T2VR are designed to push videos away from queries, i.e., suppressing the ranks of videos, while the attacks that pull videos towards selected queries, i.e., promoting the ranks of videos, remain largely unexplored. These attacks can be more impactful as attackers may gain more views/clicks for financial benefits and widespread (mis)information. To this end, we pioneer the first attack against T2VR to promote videos adversarially, dubbed the Video Promotion attack (ViPro). We further propose Modal Refinement (MoRe) to capture the finer-grained, intricate interaction between visual and textual modalities to enhance black-box transferability. Comprehensive experiments cover 2 existing baselines, 3 leading T2VR models, 3 prevailing datasets with over 10k videos, evaluated under 3 scenarios. All experiments are conducted in a multi-target setting to reflect realistic scenarios where attackers seek to promote the video regarding multiple queries simultaneously. We also evaluated our attacks for defences and imperceptibility. Overall, ViPro surpasses other baselines by over $30/10/4\%$ for white/grey/black-box settings on average. Our work highlights an overlooked vulnerability, provides a qualitative analysis on the upper/lower bound of our attacks, and offers insights into potential counterplays. Code will be publicly available at https://github.com/michaeltian108/ViPro.
Authors: Zixiong Wang, Jian Yang, Yiwei Hu, Milos Hasan, Beibei Wang
Abstract: Creating highly detailed SVBRDFs is essential for 3D content creation. The rise of high-resolution text-to-image generative models, based on diffusion transformers (DiT), suggests an opportunity to finetune them for this task. However, retargeting the models to produce multiple aligned SVBRDF maps instead of just RGB images, while achieving high efficiency and ensuring consistency across different maps, remains a challenge. In this paper, we introduce HiMat: a memory- and computation-efficient diffusion-based framework capable of generating native 4K-resolution SVBRDFs. A key challenge we address is maintaining consistency across different maps in a lightweight manner, without relying on training new VAEs or significantly altering the DiT backbone (which would damage its prior capabilities). To tackle this, we introduce the CrossStitch module, a lightweight convolutional module that captures inter-map dependencies through localized operations. Its weights are initialized such that the DiT backbone operation is unchanged before finetuning starts. HiMat enables generation with strong structural coherence and high-frequency details. Results with a large set of text prompts demonstrate the effectiveness of our approach for 4K SVBRDF generation. Further experiments suggest generalization to tasks such as intrinsic decomposition.
Authors: Junsheng Huang, Shengyu Hao, Bocheng Hu, Gaoang Wang
Abstract: Understanding dynamic 4D scenes from an egocentric perspective-modeling changes in 3D spatial structure over time-is crucial for human-machine interaction, autonomous navigation, and embodied intelligence. While existing egocentric datasets contain dynamic scenes, they lack unified 4D annotations and task-driven evaluation protocols for fine-grained spatio-temporal reasoning, especially on motion of objects and human, together with their interactions. To address this gap, we introduce EgoDynamic4D, a novel QA benchmark on highly dynamic scenes, comprising RGB-D video, camera poses, globally unique instance masks, and 4D bounding boxes. We construct 927K QA pairs accompanied by explicit Chain-of-Thought (CoT), enabling verifiable, step-by-step spatio-temporal reasoning. We design 12 dynamic QA tasks covering agent motion, human-object interaction, trajectory prediction, relation understanding, and temporal-causal reasoning, with fine-grained, multidimensional metrics. To tackle these tasks, we propose an end-to-end spatio-temporal reasoning framework that unifies dynamic and static scene information, using instance-aware feature encoding, time and camera encoding, and spatially adaptive down-sampling to compress large 4D scenes into token sequences manageable by LLMs. Experiments on EgoDynamic4D show that our method consistently outperforms baselines, validating the effectiveness of multimodal temporal modeling for egocentric dynamic scene understanding.
Authors: Ludan Zhang, Sihan Wang, Yuqi Dai, Shuofei Qiao, Qinyue Luo, Lei He
Abstract: End-to-end models are emerging as the mainstream in autonomous driving perception and planning. However, the lack of explicit supervision signals for intermediate functional modules leads to opaque operational mechanisms and limited interpretability, making it challenging for traditional methods to independently evaluate and train these modules. Pioneering in the issue, this study builds upon the feature map-truth representation similarity-based evaluation framework and proposes an independent evaluation method based on Feature Map Convergence Score (FMCS). A Dual-Granularity Dynamic Weighted Scoring System (DG-DWSS) is constructed, formulating a unified quantitative metric - Feature Map Quality Score - to enable comprehensive evaluation of the quality of feature maps generated by functional modules. A CLIP-based Feature Map Quality Evaluation Network (CLIP-FMQE-Net) is further developed, combining feature-truth encoders and quality score prediction heads to enable real-time quality analysis of feature maps generated by functional modules. Experimental results on the NuScenes dataset demonstrate that integrating our evaluation module into the training improves 3D object detection performance, achieving a 3.89 percent gain in NDS. These results verify the effectiveness of our method in enhancing feature representation quality and overall model performance.
Authors: Bowen Xue, Qixin Yan, Wenjing Wang, Hao Liu, Chen Li
Abstract: Generating high-fidelity human videos that match user-specified identities is important yet challenging in the field of generative AI. Existing methods often rely on an excessive number of training parameters and lack compatibility with other AIGC tools. In this paper, we propose Stand-In, a lightweight and plug-and-play framework for identity preservation in video generation. Specifically, we introduce a conditional image branch into the pre-trained video generation model. Identity control is achieved through restricted self-attentions with conditional position mapping, and can be learned quickly with only 2000 pairs. Despite incorporating and training just $\sim$1% additional parameters, our framework achieves excellent results in video quality and identity preservation, outperforming other full-parameter training methods. Moreover, our framework can be seamlessly integrated for other tasks, such as subject-driven video generation, pose-referenced video generation, stylization, and face swapping.
Authors: Xudong Cai, Shuo Wang, Peng Wang, Yongcai Wang, Zhaoxin Fan, Wanting Li, Tianbao Zhang, Jianrong Tao, Yeying Jin, Deying Li
Abstract: Reconstructing dense geometry for dynamic scenes from a monocular video is a critical yet challenging task. Recent memory-based methods enable efficient online reconstruction, but they fundamentally suffer from a Memory Demand Dilemma: The memory representation faces an inherent conflict between the long-term stability required for static structures and the rapid, high-fidelity detail retention needed for dynamic motion. This conflict forces existing methods into a compromise, leading to either geometric drift in static structures or blurred, inaccurate reconstructions of dynamic objects. To address this dilemma, we propose Mem4D, a novel framework that decouples the modeling of static geometry and dynamic motion. Guided by this insight, we design a dual-memory architecture: 1) The Transient Dynamics Memory (TDM) focuses on capturing high-frequency motion details from recent frames, enabling accurate and fine-grained modeling of dynamic content; 2) The Persistent Structure Memory (PSM) compresses and preserves long-term spatial information, ensuring global consistency and drift-free reconstruction for static elements. By alternating queries to these specialized memories, Mem4D simultaneously maintains static geometry with global consistency and reconstructs dynamic elements with high fidelity. Experiments on challenging benchmarks demonstrate that our method achieves state-of-the-art or competitive performance while maintaining high efficiency. Codes will be publicly available.
Authors: Fangyuan Mao, Aiming Hao, Jintao Chen, Dongxia Liu, Xiaokun Feng, Jiashu Zhu, Meiqi Wu, Chubin Chen, Jiahong Wu, Xiangxiang Chu
Abstract: Visual effects (VFX) are essential visual enhancements fundamental to modern cinematic production. Although video generation models offer cost-efficient solutions for VFX production, current methods are constrained by per-effect LoRA training, which limits generation to single effects. This fundamental limitation impedes applications that require spatially controllable composite effects, i.e., the concurrent generation of multiple effects at designated locations. However, integrating diverse effects into a unified framework faces major challenges: interference from effect variations and spatial uncontrollability during multi-VFX joint training. To tackle these challenges, we propose Omni-Effects, a first unified framework capable of generating prompt-guided effects and spatially controllable composite effects. The core of our framework comprises two key innovations: (1) LoRA-based Mixture of Experts (LoRA-MoE), which employs a group of expert LoRAs, integrating diverse effects within a unified model while effectively mitigating cross-task interference. (2) Spatial-Aware Prompt (SAP) incorporates spatial mask information into the text token, enabling precise spatial control. Furthermore, we introduce an Independent-Information Flow (IIF) module integrated within the SAP, isolating the control signals corresponding to individual effects to prevent any unwanted blending. To facilitate this research, we construct a comprehensive VFX dataset Omni-VFX via a novel data collection pipeline combining image editing and First-Last Frame-to-Video (FLF2V) synthesis, and introduce a dedicated VFX evaluation framework for validating model performance. Extensive experiments demonstrate that Omni-Effects achieves precise spatial control and diverse effect generation, enabling users to specify both the category and location of desired effects.
Authors: Zeqian Long, Mingzhe Zheng, Kunyu Feng, Xinhua Zhang, Hongyu Liu, Harry Yang, Linfeng Zhang, Qifeng Chen, Yue Ma
Abstract: While recent flow-based image editing models demonstrate general-purpose capabilities across diverse tasks, they often struggle to specialize in challenging scenarios -- particularly those involving large-scale shape transformations. When performing such structural edits, these methods either fail to achieve the intended shape change or inadvertently alter non-target regions, resulting in degraded background quality. We propose Follow-Your-Shape, a training-free and mask-free framework that supports precise and controllable editing of object shapes while strictly preserving non-target content. Motivated by the divergence between inversion and editing trajectories, we compute a Trajectory Divergence Map (TDM) by comparing token-wise velocity differences between the inversion and denoising paths. The TDM enables precise localization of editable regions and guides a Scheduled KV Injection mechanism that ensures stable and faithful editing. To facilitate a rigorous evaluation, we introduce ReShapeBench, a new benchmark comprising 120 new images and enriched prompt pairs specifically curated for shape-aware editing. Experiments demonstrate that our method achieves superior editability and visual fidelity, particularly in tasks requiring large-scale shape replacement.
Authors: Ozhan Suat, Bedirhan Uguz, Batuhan Karagoz, Muhammed Can Keles, Emre Akbas
Abstract: Despite significant progress in 3D human mesh estimation from RGB images; RGBD cameras, offering additional depth data, remain underutilized. In this paper, we present a method for accurate 3D human mesh estimation from a single RGBD view, leveraging the affordability and widespread adoption of RGBD cameras for real-world applications. A fully supervised approach for this problem, requires a dataset with RGBD image and 3D mesh label pairs. However, collecting such a dataset is costly and challenging, hence, existing datasets are small, and limited in pose and shape diversity. To overcome this data scarcity, we leverage existing Motion Capture (MoCap) datasets. We first obtain complete 3D meshes from the body models found in MoCap datasets, and create partial, single-view versions of them by projection to a virtual camera. This simulates the depth data provided by an RGBD camera from a single viewpoint. Then, we train a masked autoencoder to complete the partial, single-view mesh. During inference, our method, which we name as M$^3$ for ``Masked Mesh Modeling'', matches the depth values coming from the sensor to vertices of a template human mesh, which creates a partial, single-view mesh. We effectively recover parts of the 3D human body mesh model that are not visible, resulting in a full body mesh. M$^3$ achieves 16.8 mm and 22.0 mm per-vertex-error (PVE) on the SURREAL and CAPE datasets, respectively; outperforming existing methods that use full-body point clouds as input. We obtain a competitive 70.9 PVE on the BEHAVE dataset, outperforming a recently published RGB based method by 18.4 mm, highlighting the usefulness of depth data. Code will be released.
Authors: Jingwen He, Hongbo Liu, Jiajun Li, Ziqi Huang, Yu Qiao, Wanli Ouyang, Ziwei Liu
Abstract: Effective multi-shot generation demands purposeful, film-like transitions and strict cinematic continuity. Current methods, however, often prioritize basic visual consistency, neglecting crucial editing patterns (e.g., shot/reverse shot, cutaways) that drive narrative flow for compelling storytelling. This yields outputs that may be visually coherent but lack narrative sophistication and true cinematic integrity. To bridge this, we introduce Next Shot Generation (NSG): synthesizing a subsequent, high-quality shot that critically conforms to professional editing patterns while upholding rigorous cinematic continuity. Our framework, Cut2Next, leverages a Diffusion Transformer (DiT). It employs in-context tuning guided by a novel Hierarchical Multi-Prompting strategy. This strategy uses Relational Prompts to define overall context and inter-shot editing styles. Individual Prompts then specify per-shot content and cinematographic attributes. Together, these guide Cut2Next to generate cinematically appropriate next shots. Architectural innovations, Context-Aware Condition Injection (CACI) and Hierarchical Attention Mask (HAM), further integrate these diverse signals without introducing new parameters. We construct RawCuts (large-scale) and CuratedCuts (refined) datasets, both with hierarchical prompts, and introduce CutBench for evaluation. Experiments show Cut2Next excels in visual consistency and text fidelity. Crucially, user studies reveal a strong preference for Cut2Next, particularly for its adherence to intended editing patterns and overall cinematic continuity, validating its ability to generate high-quality, narratively expressive, and cinematically coherent subsequent shots.
Authors: Xiangyu Rui, Xiangyong Cao, Xile Zhao, Deyu Meng, Michael K. NG
Abstract: In a variational denoising model, weight in the data fidelity term plays the role of enhancing the noise-removal capability. It is profoundly correlated with noise information, while also balancing the data fidelity and regularization terms. However, the difficulty of assigning weight is expected to be substantial when the noise pattern is beyond independent identical Gaussian distribution, e.g., impulse noise, stripe noise, or a mixture of several patterns, etc. Furthermore, how to leverage weight to balance the data fidelity and regularization terms is even less evident. In this work, we propose a data-driven loss weighting (DLW) scheme to address these issues. Specifically, DLW trains a parameterized weight function (i.e., a neural network) that maps the noisy image to the weight. The training is achieved by a bilevel optimization framework, where the lower level problem is solving several denoising models with the same weight predicted by the weight function and the upper level problem minimizes the distance between the restored image and the clean image. In this way, information from both the noise and the regularization can be efficiently extracted to determine the weight function. DLW also facilitates the easy implementation of a trained weight function on denoising models. Numerical results verify the remarkable performance of DLW on improving the ability of various variational denoising models to handle different complex noise. This implies that DLW has the ability to transfer the noise knowledge at the model level to heterogeneous tasks beyond the training ones and the generalization theory underlying DLW is studied, validating its intrinsic transferability.
Authors: Monika Pytlarz, Adrian Onicas, Alessandro Crimi
Abstract: Cross-modal augmentation of Magnetic Resonance Imaging (MRI) and microscopic imaging based on the same tissue samples is promising because it can allow histopathological analysis in the absence of an underlying invasive biopsy procedure. Here, we tested a method for generating microscopic histological images from MRI scans of the human corpus callosum using conditional generative adversarial network (cGAN) architecture. To our knowledge, this is the first multimodal translation of the brain MRI to histological volumetric representation of the same sample. The technique was assessed by training paired image translation models taking sets of images from MRI scans and microscopy. The use of cGAN for this purpose is challenging because microscopy images are large in size and typically have low sample availability. The current work demonstrates that the framework reliably synthesizes histology images from MRI scans of corpus callosum, emphasizing the network's ability to train on high resolution histologies paired with relatively lower-resolution MRI scans. With the ultimate goal of avoiding biopsies, the proposed tool can be used for educational purposes.
Authors: Joshua Genova, Eric Cabrera, Vedhus Hoskere
Abstract: Surface cracks in infrastructure can lead to severe deterioration and expensive maintenance if not efficiently repaired. Manual repair methods are labor-intensive, time-consuming, and imprecise. While advancements in robotic perception and manipulation have progressed autonomous crack repair, three key challenges remain: accurate localization in the robot's coordinate frame, adaptability to varying crack sizes, and realistic validation of repairs. We present an adaptive, autonomous robotic system for surface crack detection and repair using advanced sensing technologies to enhance precision and safety for humans. A laser scanner is used to refine crack coordinates for accurate localization. Furthermore, our adaptive crack filling approach outperforms fixed speed techniques in efficiency and consistency. We validate our method using 3D printed cracks under realistic conditions, demonstrating repeatable testing. This research contributes to the field of human-robot interaction by reducing manual labor, improving safety, and streamlining maintenance operations, ultimately paving the way for more sophisticated and integrated construction robotics.
Authors: Zihan Li, Diping Song, Zefeng Yang, Deming Wang, Fei Li, Xiulan Zhang, Paul E. Kinahan, Yu Qiao
Abstract: The need for improved diagnostic methods in ophthalmology is acute, especially in the underdeveloped regions with limited access to specialists and advanced equipment. Therefore, we introduce VisionUnite, a novel vision-language foundation model for ophthalmology enhanced with clinical knowledge. VisionUnite has been pretrained on an extensive dataset comprising 1.24 million image-text pairs, and further refined using our proposed MMFundus dataset, which includes 296,379 high-quality fundus image-text pairs and 889,137 simulated doctor-patient dialogue instances. Our experiments indicate that VisionUnite outperforms existing generative foundation models such as GPT-4V and Gemini Pro. It also demonstrates diagnostic capabilities comparable to junior ophthalmologists. VisionUnite performs well in various clinical scenarios including open-ended multi-disease diagnosis, clinical explanation, and patient interaction, making it a highly versatile tool for initial ophthalmic disease screening. VisionUnite can also serve as an educational aid for junior ophthalmologists, accelerating their acquisition of knowledge regarding both common and underrepresented ophthalmic conditions. VisionUnite represents a significant advancement in ophthalmology, with broad implications for diagnostics, medical education, and understanding of disease mechanisms. The source code is at https://github.com/HUANGLIZI/VisionUnite.
Authors: Yuying Shang, Xinyi Zeng, Yutao Zhu, Xiao Yang, Zhengwei Fang, Jingyuan Zhang, Jiawei Chen, Zinan Liu, Yu Tian
Abstract: Hallucinations in large vision-language models (LVLMs) are a significant challenge, i.e., generating objects that are not presented in the visual input, which impairs their reliability. Recent studies often attribute hallucinations to a lack of understanding of visual input, yet ignore a more fundamental issue: the model's inability to effectively extract or decouple visual features. In this paper, we revisit the hallucinations in LVLMs from an architectural perspective, investigating whether the primary cause lies in the visual encoder (feature extraction) or the modal alignment module (feature decoupling). Motivated by our findings on the preliminary investigation, we propose a novel tuning strategy, PATCH, to mitigate hallucinations in LVLMs. This plug-and-play method can be integrated into various LVLMs, utilizing adaptive virtual tokens to extract object features from bounding boxes, thereby addressing hallucinations caused by insufficient decoupling of visual features. PATCH achieves state-of-the-art performance on multiple multi-modal hallucination datasets. We hope this approach provides researchers with deeper insights into the underlying causes of hallucinations in LVLMs, fostering further advancements and innovation in this field.
Authors: Sumeet Batra, Gaurav S. Sukhatme
Abstract: Generalizing vision-based reinforcement learning (RL) agents to novel environments remains a difficult and open challenge. Current trends are to collect large-scale datasets or use data augmentation techniques to prevent overfitting and improve downstream generalization. However, the computational and data collection costs increase exponentially with the number of task variations and can destabilize the already difficult task of training RL agents. In this work, we take inspiration from recent advances in computational neuroscience and propose a model, Associative Latent DisentAnglement (ALDA), that builds on standard off-policy RL towards zero-shot generalization. Specifically, we revisit the role of latent disentanglement in RL and show how combining it with a model of associative memory achieves zero-shot generalization on difficult task variations without relying on data augmentation. Finally, we formally show that data augmentation techniques are a form of weak disentanglement and discuss the implications of this insight.
Authors: Wei Guo, Heng Wang, Jianbo Ma, Weidong Cai
Abstract: Audio synthesis has broad applications in multimedia. Recent advancements have made it possible to generate relevant audios from inputs describing an audio scene, such as images or texts. However, the immersiveness and expressiveness of the generation are limited. One possible problem is that existing methods solely rely on the global scene and overlook details of local sounding objects (i.e., sound sources). To address this issue, we propose a Sound Source-Aware Audio (SS2A) generator. SS2A is able to locally perceive multimodal sound sources from a scene with visual detection and cross-modality translation. It then contrastively learns a Cross-Modal Sound Source (CMSS) Manifold to semantically disambiguate each source. Finally, we attentively mix their CMSS semantics into a rich audio representation, from which a pretrained audio generator outputs the sound. To model the CMSS manifold, we curate a novel single-sound-source visual-audio dataset VGGS3 from VGGSound. We also design a Sound Source Matching Score to clearly measure localized audio relevance. With the effectiveness of explicit sound source modeling, SS2A achieves state-of-the-art performance in extensive image-to-audio tasks. We also qualitatively demonstrate SS2A's ability to achieve intuitive synthesis control by compositing vision, text, and audio conditions. Furthermore, we show that our sound source modeling can achieve competitive video-to-audio performance with a straightforward temporal aggregation mechanism.
Authors: Fangwei Zhong, Kui Wu, Churan Wang, Hao Chen, Hai Ci, Zhoujun Li, Yizhou Wang
Abstract: We introduce UnrealZoo, a collection of over 100 photo-realistic 3D virtual worlds built on Unreal Engine, designed to reflect the complexity and variability of open-world environments. We also provide a rich variety of playable entities, including humans, animals, robots, and vehicles for embodied AI research. We extend UnrealCV with optimized APIs and tools for data collection, environment augmentation, distributed training, and benchmarking. These improvements achieve significant improvements in the efficiency of rendering and communication, enabling advanced applications such as multi-agent interactions. Our experimental evaluation across visual navigation and tracking tasks reveals two key insights: 1) environmental diversity provides substantial benefits for developing generalizable reinforcement learning (RL) agents, and 2) current embodied agents face persistent challenges in open-world scenarios, including navigation in unstructured terrain, adaptation to unseen morphologies, and managing latency in the close-loop control systems for interacting in highly dynamic objects. UnrealZoo thus serves as both a comprehensive testing ground and a pathway toward developing more capable embodied AI systems for real-world deployment.
Authors: Yaqian Chen, Hanxue Gu, Yuwen Chen, Jichen Yang, Haoyu Dong, Joseph Y. Cao, Adrian Camarena, Christopher Mantyh, Roy Colglazier, Maciej A. Mazurowski
Abstract: Body composition assessment using CT images can potentially be used for a number of clinical applications, including the prognostication of cardiovascular outcomes, evaluation of metabolic health, monitoring of disease progression, assessment of nutritional status, prediction of treatment response in oncology, and risk stratification for surgical and critical care outcomes. While multiple groups have developed in-house segmentation tools for this analysis, there are very limited publicly available tools that could be consistently used across different applications. To mitigate this gap, we present a publicly accessible, end-to-end segmentation and feature calculation model specifically for CT body composition analysis. Our model performs segmentation of skeletal muscle, subcutaneous adipose tissue (SAT), and visceral adipose tissue (VAT) across the chest, abdomen, and pelvis area in axial CT images. It also provides various body composition metrics, including muscle density, visceral-to-subcutaneous fat (VAT/SAT) ratio, muscle area/volume, and skeletal muscle index (SMI), supporting both 2D and 3D assessments. To evaluate the model, the segmentation was applied to both internal and external datasets, with body composition metrics analyzed across different age, sex, and race groups. The model achieved high dice coefficients on both internal and external datasets, exceeding 89% for skeletal muscle, SAT, and VAT segmentation. The model outperforms the benchmark by 2.40% on skeletal muscle and 10.26% on SAT compared to the manual annotations given by the publicly available dataset. Body composition metrics show mean relative absolute errors (MRAEs) under 10% for all measures. Furthermore, the model provided muscular fat segmentation with a Dice coefficient of 56.27%, which can be utilized for additional analyses as needed.
Authors: Fan Yang, Dongsheng Luo, Wenrui Chen, Jiacheng Lin, Junjie Cai, Kailun Yang, Zhiyong Li, Yaonan Wang
Abstract: Functional dexterous grasping requires precise hand-object interaction, going beyond simple gripping. Existing affordance-based methods primarily predict coarse interaction regions and cannot directly constrain the grasping posture, leading to a disconnection between visual perception and manipulation. To address this issue, we propose a multi-keypoint affordance representation for functional dexterous grasping, which directly encodes task-driven grasp configurations by localizing functional contact points. Our method introduces Contact-guided Multi-Keypoint Affordance (CMKA), leveraging human grasping experience images for weak supervision combined with Large Vision Models for fine affordance feature extraction, achieving generalization while avoiding manual keypoint annotations. Additionally, we present a Keypoint-based Grasp matrix Transformation (KGT) method, ensuring spatial consistency between hand keypoints and object contact points, thus providing a direct link between visual perception and dexterous grasping actions. Experiments on public real-world FAH datasets, IsaacGym simulation, and challenging robotic tasks demonstrate that our method significantly improves affordance localization accuracy, grasp consistency, and generalization to unseen tools and tasks, bridging the gap between visual affordance learning and dexterous robotic manipulation. The source code and demo videos are publicly available at https://github.com/PopeyePxx/MKA.
Authors: Cheng Yuan, Zhening Liu, Jiashu Lv, Jiawei Shao, Yufei Jiang, Jun Zhang, Xuelong Li
Abstract: With the rapid development of large multimodal models (LMMs), multimodal understanding applications are emerging. As most LMM inference requests originate from edge devices with limited computational capabilities, the predominant inference pipeline involves directly forwarding the input data to an edge server which handles all computations. However, this approach introduces high transmission latency due to limited uplink bandwidth of edge devices and significant computation latency caused by the prohibitive number of visual tokens, thus hindering delay-sensitive tasks and degrading user experience. To address this challenge, we propose a task-oriented feature compression (TOFC) method for multimodal understanding in a device-edge co-inference framework, where visual features are merged by clustering and encoded by a learnable and selective entropy model before feature projection. Specifically, we employ density peaks clustering based on K nearest neighbors to reduce the number of visual features, thereby minimizing both data transmission and computational complexity. Subsequently, a learnable entropy model with hyperprior is utilized to encode and decode merged features, further reducing transmission overhead. To enhance compression efficiency, multiple entropy models are adaptively selected based on the characteristics of the visual features, enabling a more accurate estimation of the probability distribution. Comprehensive experiments on seven visual question answering benchmarks validate the effectiveness of the proposed TOFC method. Results show that TOFC achieves up to 52% reduction in data transmission overhead and 63% reduction in system latency while maintaining identical task performance, compared with neural compression ELIC.
Authors: Euclid Collaboration, G. Stevens, S. Fotopoulou, M. N. Bremer, T. Matamoro Zatarain, K. Jahnke, B. Margalef-Bentabol, M. Huertas-Company, M. J. Smith, M. Walmsley, M. Salvato, M. Mezcua, A. Paulino-Afonso, M. Siudek, M. Talia, F. Ricci, W. Roster, N. Aghanim, B. Altieri, S. Andreon, H. Aussel, C. Baccigalupi, M. Baldi, S. Bardelli, P. Battaglia, A. Biviano, A. Bonchi, E. Branchini, M. Brescia, J. Brinchmann, S. Camera, G. Ca\~nas-Herrera, V. Capobianco, C. Carbone, J. Carretero, M. Castellano, G. Castignani, S. Cavuoti, K. C. Chambers, A. Cimatti, C. Colodro-Conde, G. Congedo, C. J. Conselice, L. Conversi, Y. Copin, A. Costille, F. Courbin, H. M. Courtois, M. Cropper, A. Da Silva, H. Degaudenzi, G. De Lucia, C. Dolding, H. Dole, M. Douspis, F. Dubath, X. Dupac, S. Dusini, S. Escoffier, M. Farina, S. Ferriol, K. George, C. Giocoli, B. R. Granett, A. Grazian, F. Grupp, S. V. H. Haugan, I. M. Hook, F. Hormuth, A. Hornstrup, P. Hudelot, M. Jhabvala, E. Keih\"anen, S. Kermiche, A. Kiessling, M. Kilbinger, B. Kubik, M. K\"ummel, H. Kurki-Suonio, Q. Le Boulc'h, A. M. C. Le Brun, D. Le Mignant, P. B. Lilje, V. Lindholm, I. Lloro, G. Mainetti, D. Maino, E. Maiorano, O. Marggraf, M. Martinelli, N. Martinet, F. Marulli, R. Massey, S. Maurogordato, H. J. McCracken, E. Medinaceli, S. Mei, M. Melchior, M. Meneghetti, E. Merlin, G. Meylan, A. Mora, M. Moresco, L. Moscardini, R. Nakajima, C. Neissner, S. -M. Niemi, C. Padilla, S. Paltani, F. Pasian, K. Pedersen, W. J. Percival, V. Pettorino, G. Polenta, M. Poncet, L. A. Popa, L. Pozzetti, F. Raison, R. Rebolo, A. Renzi, J. Rhodes, G. Riccio, E. Romelli, M. Roncarelli, R. Saglia, A. G. S\'anchez, D. Sapone, J. A. Schewtschenko, M. Schirmer, P. Schneider, T. Schrabback, A. Secroun, S. Serrano, P. Simon, C. Sirignano, G. Sirri, J. Skottfelt, L. Stanco, J. Steinwagner, P. Tallada-Cresp\'i, A. N. Taylor, I. Tereno, S. Toft, R. Toledo-Moreo, F. Torradeflot, I. Tutusaus, L. Valenziano, J. Valiviita, T. Vassallo, G. Verdoes Kleijn, A. Veropalumbo, Y. Wang, J. Weller, A. Zacchei, G. Zamorani, F. M. Zerbi, I. A. Zinchenko, E. Zucca, V. Allevato, M. Ballardini, M. Bolzonella, E. Bozzo, C. Burigana, R. Cabanac, A. Cappi, J. A. Escartin Vigo, L. Gabarra, W. G. Hartley, J. Mart\'in-Fleitas, S. Matthew, R. B. Metcalf, A. Pezzotta, M. P\"ontinen, I. Risso, V. Scottez, M. Sereno, M. Tenti, M. Wiesmann, Y. Akrami, S. Alvi, I. T. Andika, S. Anselmi, M. Archidiacono, F. Atrio-Barandela, D. Bertacca, M. Bethermin, L. Bisigello, A. Blanchard, L. Blot, S. Borgani, M. L. Brown, S. Bruton, A. Calabro, F. Caro, T. Castro, F. Cogato, S. Davini, G. Desprez, A. D\'iaz-S\'anchez, J. J. Diaz, S. Di Domizio, J. M. Diego, P. -A. Duc, A. Enia, Y. Fang, A. G. Ferrari, A. Finoguenov, A. Fontana, A. Franco, J. Garc\'ia-Bellido, T. Gasparetto, V. Gautard, E. Gaztanaga, F. Giacomini, F. Gianotti, M. Guidi, C. M. Gutierrez, A. Hall, S. Hemmati, H. Hildebrandt, J. Hjorth, J. J. E. Kajava, Y. Kang, V. Kansal, D. Karagiannis, C. C. Kirkpatrick, S. Kruk, L. Legrand, M. Lembo, F. Lepori, G. Leroy, J. Lesgourgues, L. Leuzzi, T. I. Liaudat, J. Macias-Perez, M. Magliocchetti, F. Mannucci, R. Maoli, C. J. A. P. Martins, L. Maurin, M. Miluzio, P. Monaco, G. Morgante, K. Naidoo, A. Navarro-Alsina, F. Passalacqua, K. Paterson, L. Patrizii, A. Pisani, D. Potter, S. Quai, M. Radovich, P. -F. Rocci, G. Rodighiero, S. Sacquegna, M. Sahl\'en, D. B. Sanders, E. Sarpa, A. Schneider, M. Schultheis, D. Sciotti, E. Sellentin, F. Shankar, L. C. Smith, K. Tanidis, G. Testera, R. Teyssier, S. Tosi, A. Troja, M. Tucci, C. Valieri, D. Vergani, G. Verza, N. A. Walton
Abstract: Light emission from galaxies exhibit diverse brightness profiles, influenced by factors such as galaxy type, structural features and interactions with other galaxies. Elliptical galaxies feature more uniform light distributions, while spiral and irregular galaxies have complex, varied light profiles due to their structural heterogeneity and star-forming activity. In addition, galaxies with an active galactic nucleus (AGN) feature intense, concentrated emission from gas accretion around supermassive black holes, superimposed on regular galactic light, while quasi-stellar objects (QSO) are the extreme case of the AGN emission dominating the galaxy. The challenge of identifying AGN and QSO has been discussed many times in the literature, often requiring multi-wavelength observations. This paper introduces a novel approach to identify AGN and QSO from a single image. Diffusion models have been recently developed in the machine-learning literature to generate realistic-looking images of everyday objects. Utilising the spatial resolving power of the Euclid VIS images, we created a diffusion model trained on one million sources, without using any source pre-selection or labels. The model learns to reconstruct light distributions of normal galaxies, since the population is dominated by them. We condition the prediction of the central light distribution by masking the central few pixels of each source and reconstruct the light according to the diffusion model. We further use this prediction to identify sources that deviate from this profile by examining the reconstruction error of the few central pixels regenerated in each source's core. Our approach, solely using VIS imaging, features high completeness compared to traditional methods of AGN and QSO selection, including optical, near-infrared, mid-infrared, and X-rays.
Authors: Jixuan Leng, Chengsong Huang, Langlin Huang, Bill Yuchen Lin, William W. Cohen, Haohan Wang, Jiaxin Huang
Abstract: Existing reasoning evaluation frameworks for Large Language Models (LLMs) and Large Vision-Language Models (LVLMs) predominantly assess either text-based reasoning or vision-language understanding capabilities, with limited dynamic interplay between textual and visual constraints. To address this limitation, we introduce CrossWordBench, a benchmark designed to evaluate the reasoning capabilities of both LLMs and LVLMs through the medium of crossword puzzles -- a task requiring multimodal adherence to semantic constraints from text-based clues and intersectional constraints from visual grid structures. CrossWordBench leverages a controllable puzzle generation framework that produces puzzles in two formats (text and image), supports adjustable difficulty through prefill ratio control, and offers different evaluation strategies, ranging from direct puzzle solving to interactive modes. Our extensive evaluation of over 20 models reveals that reasoning LLMs substantially outperform non-reasoning models by effectively leveraging crossing-letter constraints. We further demonstrate that LVLMs struggle with the task, showing a strong correlation between their puzzle-solving performance and grid-parsing accuracy. Our findings highlight limitations of the reasoning capabilities of current LLMs and LVLMs, and provide an effective approach for creating multimodal constrained tasks for future evaluations.
Authors: Minjong Cheon
Abstract: Recent advances in AI-based weather forecasting models, such as FourCastNet, Pangu-Weather, and GraphCast, have demonstrated the remarkable ability of deep learning to emulate complex atmospheric dynamics. Building on this momentum, we propose Mj\"olnir, a novel deep learning-based framework for global lightning flash density parameterization. Trained on ERA5 atmospheric predictors and World Wide Lightning Location Network (WWLLN) observations at a daily temporal resolution and 1 degree spatial resolution, Mj\"olnir captures the nonlinear mapping between large-scale environmental conditions and lightning activity. The model architecture is based on the InceptionNeXt backbone with SENet, and a multi-task learning strategy to simultaneously predict lightning occurrence and magnitude. Extensive evaluations yield that Mollnir accurately reproduces the global distribution, seasonal variability, and regional characteristics of lightning activity, achieving a global Pearson correlation coefficient of 0.96 for annual mean fields. These results suggest that Mj\"olnir serves not only as an effective data-driven global lightning parameterization but also as a promising AI-based scheme for next-generation Earth system models (AI-ESMs).
Authors: Md Rakibul Hasan, Pouria Behnoudfar, Dan MacKinlay, Thomas Poulet
Abstract: Machine Learning, particularly Generative Adversarial Networks (GANs), has revolutionised Super-Resolution (SR). However, generated images often lack physical meaningfulness, which is essential for scientific applications. Our approach, PC-SRGAN, enhances image resolution while ensuring physical consistency for interpretable simulations. PC-SRGAN significantly improves both the Peak Signal-to-Noise Ratio and the Structural Similarity Index Measure compared to conventional SR methods, even with limited training data (e.g., only 13% of training data is required to achieve performance similar to SRGAN). Beyond SR, PC-SRGAN augments physically meaningful machine learning, incorporating numerically justified time integrators and advanced quality metrics. These advancements promise reliable and causal machine-learning models in scientific domains. A significant advantage of PC-SRGAN over conventional SR techniques is its physical consistency, which makes it a viable surrogate model for time-dependent problems. PC-SRGAN advances scientific machine learning by improving accuracy and efficiency, enhancing process understanding, and broadening applications to scientific research. We publicly release the complete source code of PC-SRGAN and all experiments at https://github.com/hasan-rakibul/PC-SRGAN.
Authors: Bimal Kumar Ray
Abstract: This paper proposes a fast and unsupervised scheme for the polygonal approximation of a closed digital curve. It is demonstrated that the approximation scheme is faster than state-of-the-art approximation and is competitive with Rosin's measure and aesthetic aspects. The scheme comprises of three phases: initial segmentation, iterative vertex insertion, iterative merging, and vertex adjustment. The initial segmentation is used to detect sharp turns, that is, vertices that seemingly have high curvature. It is likely that some of the important vertices with low curvature might have been missed in the first phase; therefore, iterative vertex insertion is used to add vertices in a region where the curvature changes slowly but steadily. The initial phase may pick up some undesirable vertices, and thus merging is used to eliminate redundant vertices. Finally, vertex adjustment was used to enhance the aesthetic appearance of the approximation. The quality of the approximations was measured using the Rosin's method. The robustness of the proposed scheme with respect to geometric transformation was observed.
Authors: Phillipe R. Sampaio, Helene Maxcici
Abstract: This paper investigates a novel approach to unsupervised document clustering by leveraging multimodal embeddings as input to clustering algorithms such as $k$-Means, DBSCAN, a combination of HDBSCAN and $k$-NN, and BIRCH. Our method aims to achieve a finer-grained document understanding by not only grouping documents at the type level (e.g., invoices, purchase orders), but also distinguishing between different templates within the same document category. This is achieved by using embeddings that capture textual content, layout information, and visual features of documents. We evaluated the effectiveness of this approach using embeddings generated by several state-of-the-art pre-trained multimodal models, including SBERT, LayoutLMv1, LayoutLMv3, DiT, Donut, ColPali, Gemma3, and InternVL3. Our findings demonstrate the potential of multimodal embeddings to significantly enhance document clustering, offering benefits for various applications in intelligent document processing, document layout analysis, and unsupervised document classification. This work provides valuable insight into the advantages and limitations of different multimodal models for this task and opens new avenues for future research to understand and organize document collections.
Authors: Maxence Boels, Harry Robertshaw, Thomas C Booth, Prokar Dasgupta, Alejandro Granados, Sebastien Ourselin
Abstract: Surgical action planning requires predicting future instrument-verb-target triplets for real-time assistance. While teleoperated robotic surgery provides natural expert demonstrations for imitation learning (IL), reinforcement learning (RL) could potentially discover superior strategies through exploration. We present the first comprehensive comparison of IL versus RL for surgical action planning on CholecT50. Our Dual-task Autoregressive Imitation Learning (DARIL) baseline achieves 34.6% action triplet recognition mAP and 33.6% next frame prediction mAP with smooth planning degradation to 29.2% at 10-second horizons. We evaluated three RL variants: world model-based RL, direct video RL, and inverse RL enhancement. Surprisingly, all RL approaches underperformed DARIL i.e. world model RL dropped to 3.1% mAP at 10s while direct video RL achieved only 15.9%. Our analysis reveals that distribution matching on expert-annotated test sets systematically favors IL over potentially valid RL policies that differ from training demonstrations. This challenges assumptions about RL superiority in sequential decision making and provides crucial insights for surgical AI development.
Authors: Abhijeet Narang, Parul Gupta, Liuyijia Su, Abhinav Dhall
Abstract: This demonstration paper presents $\mathbf{LayLens}$, a tool aimed to make deepfake understanding easier for users of all educational backgrounds. While prior works often rely on outputs containing technical jargon, LayLens bridges the gap between model reasoning and human understanding through a three-stage pipeline: (1) explainable deepfake detection using a state-of-the-art forgery localization model, (2) natural language simplification of technical explanations using a vision-language model, and (3) visual reconstruction of a plausible original image via guided image editing. The interface presents both technical and layperson-friendly explanations in addition to a side-by-side comparison of the uploaded and reconstructed images. A user study with 15 participants shows that simplified explanations significantly improve clarity and reduce cognitive load, with most users expressing increased confidence in identifying deepfakes. LayLens offers a step toward transparent, trustworthy, and user-centric deepfake forensics.
Authors: Aviad Golan, Gregory Zin, Zahra Ahmed, Emily Bates, Toby Bell, Pol Francesch Huc, Samuel Y. W. Low, Juergen Bosse, Simone D'Amico
Abstract: In spacecraft Rendezvous, Proximity Operations (RPO), and Formation Flying (FF), the Guidance Navigation and Control (GNC) system is safety-critical and must meet strict performance requirements. However, validating such systems is challenging due to the complexity of the space environment, necessitating a verification and validation (V&V) process that bridges simulation and real-world behavior. The key contribution of this paper is a unified, end-to-end digital and robotic twinning framework that enables software- and hardware-in-the-loop testing for multi-modal GNC systems. The robotic twin includes three testbeds at Stanford's Space Rendezvous Laboratory (SLAB): the GNSS and Radiofrequency Autonomous Navigation Testbed for Distributed Space Systems (GRAND) to validate RF-based navigation techniques, and the Testbed for Rendezvous and Optical Navigation (TRON) and Optical Stimulator (OS) to validate vision-based methods. The test article for this work is an integrated multi-modal GNC software stack for RPO and FF developed at SLAB. This paper introduces the hybrid framework and summarizes calibration and error characterization for the robotic twin. Then, the GNC stack's performance and robustness is characterized using the integrated digital and robotic twinning pipeline for a full-range RPO mission scenario in Low-Earth Orbit (LEO). The results shown in the paper demonstrate consistency between digital and robotic twins, validating the hybrid twinning pipeline as a reliable framework for realistic assessment and verification of GNC systems.
Authors: Akwasi Asare, Mary Sagoe, Justice Williams Asare
Abstract: Automated segmentation of diabetic foot ulcers (DFUs) plays a critical role in clinical diagnosis, therapeutic planning, and longitudinal wound monitoring. However, this task remains challenging due to the heterogeneous appearance, irregular morphology, and complex backgrounds associated with ulcer regions in clinical photographs. Traditional convolutional neural networks (CNNs), such as U-Net, provide strong localization capabilities but struggle to model long-range spatial dependencies due to their inherently limited receptive fields. To address this, we propose FUTransUNet, a hybrid architecture that integrates the global attention mechanism of Vision Transformers (ViTs) into the U-Net framework. This combination allows the model to extract global contextual features while maintaining fine-grained spatial resolution through skip connections and an effective decoding pathway. We trained and validated FUTransUNet on the public Foot Ulcer Segmentation Challenge (FUSeg) dataset. FUTransUNet achieved a training Dice Coefficient of 0.8679, an IoU of 0.7672, and a training loss of 0.0053. On the validation set, the model achieved a Dice Coefficient of 0.8751, an IoU of 0.7780, and a validation loss of 0.009045. To ensure clinical transparency, we employed Grad-CAM visualizations, which highlighted model focus areas during prediction. These quantitative outcomes clearly demonstrate that our hybrid approach successfully integrates global and local feature extraction paradigms, thereby offering a highly robust, accurate, explainable, and interpretable solution and clinically translatable solution for automated foot ulcer analysis. The approach offers a reliable, high-fidelity solution for DFU segmentation, with implications for improving real-world wound assessment and patient care.
Authors: Zeyi Sun, Ziyu Liu, Yuhang Zang, Yuhang Cao, Xiaoyi Dong, Tong Wu, Dahua Lin, Jiaqi Wang
Abstract: Repurposing large vision-language models (LVLMs) as computer use agents (CUAs) has led to substantial breakthroughs, primarily driven by human-labeled data. However, these models often struggle with novel and specialized software, particularly in scenarios lacking human annotations. To address this challenge, we propose SEAgent, an agentic self-evolving framework enabling CUAs to autonomously evolve through interactions with unfamiliar software. Specifically, SEAgent empowers computer-use agents to autonomously master novel software environments via experiential learning, where agents explore new software, learn through iterative trial-and-error, and progressively tackle auto-generated tasks organized from simple to complex. To achieve this goal, we design a World State Model for step-wise trajectory assessment, along with a Curriculum Generator that generates increasingly diverse and challenging tasks. The agent's policy is updated through experiential learning, comprised of adversarial imitation of failure actions and Group Relative Policy Optimization (GRPO) on successful ones. Furthermore, we introduce a specialist-to-generalist training strategy that integrates individual experiential insights from specialist agents, facilitating the development of a stronger generalist CUA capable of continuous autonomous evolution. This unified agent ultimately achieves performance surpassing ensembles of individual specialist agents on their specialized software. We validate the effectiveness of SEAgent across five novel software environments within OS-World. Our approach achieves a significant improvement of 23.2% in success rate, from 11.3% to 34.5%, over a competitive open-source CUA, i.e., UI-TARS.
Authors: Anqing Jiang, Yu Gao, Yiru Wang, Zhigang Sun, Shuo Wang, Yuwen Heng, Hao Sun, Shichen Tang, Lijuan Zhu, Jinhao Chai, Jijun Wang, Zichong Gu, Hao Jiang, Li Sun
Abstract: Vision-Language-Action (VLA) models have demonstrated potential in autonomous driving. However, two critical challenges hinder their development: (1) Existing VLA architectures are typically based on imitation learning in open-loop setup which tends to capture the recorded behaviors in the dataset, leading to suboptimal and constrained performance, (2) Close-loop training relies heavily on high-fidelity sensor simulation, where domain gaps and computational inefficiencies pose significant barriers. In this paper, we introduce IRL-VLA, a novel close-loop Reinforcement Learning via \textbf{I}nverse \textbf{R}einforcement \textbf{L}earning reward world model with a self-built VLA approach. Our framework proceeds in a three-stage paradigm: In the first stage, we propose a VLA architecture and pretrain the VLA policy via imitation learning. In the second stage, we construct a lightweight reward world model via inverse reinforcement learning to enable efficient close-loop reward computation. To further enhance planning performance, finally, we design specialized reward world model guidence reinforcement learning via PPO(Proximal Policy Optimization) to effectively balance the safety incidents, comfortable driving, and traffic efficiency. Our approach achieves state-of-the-art performance in NAVSIM v2 end-to-end driving benchmark, 1st runner up in CVPR2025 Autonomous Grand Challenge. We hope that our framework will accelerate VLA research in close-loop autonomous driving.
Authors: Lixuan He, Jie Feng, Yong Li
Abstract: Large Language Models (LLMs) are typically fine-tuned for reasoning tasks through a two-stage pipeline of Supervised Fine-Tuning (SFT) followed by Reinforcement Learning (RL), a process fraught with catastrophic forgetting and suboptimal trade-offs between imitation and exploration. Recent single-stage methods attempt to unify SFT and RL using heuristics, but lack a principled mechanism for dynamically balancing the two paradigms. In this paper, we reframe this challenge through the theoretical lens of \textbf{implicit rewards}, viewing SFT and RL not as distinct methods but as complementary reward signals. We introduce \textbf{Adaptive Meta Fine-Tuning (AMFT)}, a novel single-stage algorithm that learns the optimal balance between SFT's implicit, path-level reward and RL's explicit, outcome-based reward. The core of AMFT is a \textbf{meta-gradient adaptive weight controller} that treats the SFT-RL balance as a learnable parameter, dynamically optimizing it to maximize long-term task performance. This forward-looking approach, regularized by policy entropy for stability, autonomously discovers an effective training curriculum. We conduct a comprehensive evaluation on challenging benchmarks spanning mathematical reasoning, abstract visual reasoning (General Points), and vision-language navigation (V-IRL). AMFT consistently establishes a new state-of-the-art and demonstrats superior generalization on out-of-distribution (OOD) tasks. Ablation studies and training dynamic analysis confirm that the meta-learning controller is crucial for AMFT's stability, sample efficiency, and performance, offering a more principled and effective paradigm for LLM alignment. Our codes are open-sourced via https://github.com/hlxtsyj/AMFT.