Authors: Anran Yu, Wei Feng, Yaochen Zhang, Xiang Li, Lei Meng, Lei Wu, Xiangxu Meng
Abstract: The personalized text-to-image generation has rapidly advanced with the emergence of Stable Diffusion. Existing methods, which typically fine-tune models using embedded identifiers, often struggle with insufficient stylization and inaccurate image content due to reduced textual controllability. In this paper, we propose style refinement and content preservation strategies. The style refinement strategy leverages the semantic information of visual reasoning prompts and reference images to optimize style embeddings, allowing a more precise and consistent representation of style information. The content preservation strategy addresses the content bias problem by preserving the model's generalization capabilities, ensuring enhanced textual controllability without compromising stylization. Experimental results verify that our approach achieves superior performance in generating consistent and personalized text-to-image outputs.
Authors: Yuan-Hong Liao, Sven Elflein, Liu He, Laura Leal-Taix\'e, Yejin Choi, Sanja Fidler, David Acuna
Abstract: Recent reasoning models through test-time scaling have demonstrated that long chain-of-thoughts can unlock substantial performance boosts in hard reasoning tasks such as math and code. However, the benefit of such long thoughts for system-2 reasoning is relatively less explored in other domains such as perceptual tasks where shallower, system-1 reasoning seems sufficient. In this paper, we introduce LongPerceptualThoughts, a new synthetic dataset with 30K long-thought traces for perceptual tasks. The key challenges in synthesizing elaborate reasoning thoughts for perceptual tasks are that off-the-shelf models are not yet equipped with such thinking behavior and that it is not straightforward to build a reliable process verifier for perceptual tasks. Thus, we propose a novel three-stage data synthesis framework that first synthesizes verifiable multiple-choice questions from dense image descriptions, then extracts simple CoTs from VLMs for those verifiable problems, and finally expands those simple thoughts to elaborate long thoughts via frontier reasoning models. In controlled experiments with a strong instruction-tuned 7B model, we demonstrate notable improvements over existing visual reasoning data-generation methods. Our model, trained on the generated dataset, achieves an average +3.4 points improvement over 5 vision-centric benchmarks, including +11.8 points on V$^*$ Bench. Notably, despite being tuned for vision tasks, it also improves performance on the text reasoning benchmark, MMLU-Pro, by +2 points.
Authors: Wei Fang, Priyadarshini Panda
Abstract: The neuromorphic event cameras have overwhelming advantages in temporal resolution, power efficiency, and dynamic range compared to traditional cameras. However, the event cameras output asynchronous, sparse, and irregular events, which are not compatible with mainstream computer vision and deep learning methods. Various methods have been proposed to solve this issue but at the cost of long preprocessing procedures, losing temporal resolutions, or being incompatible with massively parallel computation. Inspired by the great success of the word to vector, we summarize the similarities between words and events, then propose the first event to vector (event2vec) representation. We validate event2vec on classifying the ASL-DVS dataset, showing impressive parameter efficiency, accuracy, and speed than previous graph/image/voxel-based representations. Beyond task performance, the most attractive advantage of event2vec is that it aligns events to the domain of natural language processing, showing the promising prospect of integrating events into large language and multimodal models. Our codes, models, and training logs are available at https://github.com/fangwei123456/event2vec.
Authors: Zhiqiu Lin, Siyuan Cen, Daniel Jiang, Jay Karhade, Hewei Wang, Chancharik Mitra, Tiffany Ling, Yuhan Huang, Sifan Liu, Mingyu Chen, Rushikesh Zawar, Xue Bai, Yilun Du, Chuang Gan, Deva Ramanan
Abstract: We introduce CameraBench, a large-scale dataset and benchmark designed to assess and improve camera motion understanding. CameraBench consists of ~3,000 diverse internet videos, annotated by experts through a rigorous multi-stage quality control process. One of our contributions is a taxonomy of camera motion primitives, designed in collaboration with cinematographers. We find, for example, that some motions like "follow" (or tracking) require understanding scene content like moving subjects. We conduct a large-scale human study to quantify human annotation performance, revealing that domain expertise and tutorial-based training can significantly enhance accuracy. For example, a novice may confuse zoom-in (a change of intrinsics) with translating forward (a change of extrinsics), but can be trained to differentiate the two. Using CameraBench, we evaluate Structure-from-Motion (SfM) and Video-Language Models (VLMs), finding that SfM models struggle to capture semantic primitives that depend on scene content, while VLMs struggle to capture geometric primitives that require precise estimation of trajectories. We then fine-tune a generative VLM on CameraBench to achieve the best of both worlds and showcase its applications, including motion-augmented captioning, video question answering, and video-text retrieval. We hope our taxonomy, benchmark, and tutorials will drive future efforts towards the ultimate goal of understanding camera motions in any video.
Authors: Scott Sorensen, Wayne Treible, Robert Wagner, Andrew D. Gilliam, Todd Rovito, Joseph L. Mundy
Abstract: Physics driven image simulation allows for the modeling and creation of realistic imagery beyond what is afforded by typical rendering pipelines. We aim to automatically generate a physically realistic scene for simulation of a given region using satellite imagery to model the scene geometry, drive material estimates, and populate the scene with dynamic elements. We present automated techniques to utilize satellite imagery throughout the simulated scene to expedite scene construction and decrease manual overhead. Our technique does not use lidar, enabling simulations that could not be constructed previously. To develop a 3D scene, we model the various components of the real location, addressing the terrain, modelling man-made structures, and populating the scene with smaller elements such as vegetation and vehicles. To create the scene we begin with a Digital Surface Model, which serves as the basis for scene geometry, and allows us to reason about the real location in a common 3D frame of reference. These simulated scenes can provide increased fidelity with less manual intervention for novel locations on earth, and can facilitate algorithm development, and processing pipelines for imagery ranging from UV to LWIR $(200nm-20\mu m)$.
Authors: Huimin Zeng, Jiacheng Li, Zhiwei Xiong
Abstract: As a widely adopted technique in data transmission, video compression effectively reduces the size of files, making it possible for real-time cloud computing. However, it comes at the cost of visual quality, posing challenges to the robustness of downstream vision models. In this work, we present a versatile codec-aware enhancement framework that reuses codec information to adaptively enhance videos under different compression settings, assisting various downstream vision tasks without introducing computation bottleneck. Specifically, the proposed codec-aware framework consists of a compression-aware adaptation (CAA) network that employs a hierarchical adaptation mechanism to estimate parameters of the frame-wise enhancement network, namely the bitstream-aware enhancement (BAE) network. The BAE network further leverages temporal and spatial priors embedded in the bitstream to effectively improve the quality of compressed input frames. Extensive experimental results demonstrate the superior quality enhancement performance of our framework over existing enhancement methods, as well as its versatility in assisting multiple downstream tasks on compressed videos as a plug-and-play module. Code and models are available at https://huimin-zeng.github.io/PnP-VCVE/.
Authors: Chen Zhao, Anjum Shaik, Joyce H. Keyak, Nancy E. Lane, Jeffrey D. Deng, Kuan-Jui Su, Qiuying Sha, Hui Shen, Hong-Wen Deng, Weihua Zhou
Abstract: Hip fractures represent a major health concern, particularly among the elderly, often leading decreased mobility and increased mortality. Early and accurate detection of at risk individuals is crucial for effective intervention. In this study, we propose Iterative Cross Graph Matching for Hip Fracture Risk Assessment (ICGM-FRAX), a novel approach for predicting hip fractures using Dual-energy X-ray Absorptiometry (DXA) images. ICGM-FRAX involves iteratively comparing a test (subject) graph with multiple template graphs representing the characteristics of hip fracture subjects to assess the similarity and accurately to predict hip fracture risk. These graphs are obtained as follows. The DXA images are separated into multiple regions of interest (RoIs), such as the femoral head, shaft, and lesser trochanter. Radiomic features are then calculated for each RoI, with the central coordinates used as nodes in a graph. The connectivity between nodes is established according to the Euclidean distance between these coordinates. This process transforms each DXA image into a graph, where each node represents a RoI, and edges derived by the centroids of RoIs capture the spatial relationships between them. If the test graph closely matches a set of template graphs representing subjects with incident hip fractures, it is classified as indicating high hip fracture risk. We evaluated our method using 547 subjects from the UK Biobank dataset, and experimental results show that ICGM-FRAX achieved a sensitivity of 0.9869, demonstrating high accuracy in predicting hip fractures.
Authors: Ankit Dhiman, Manan Shah, R Venkatesh Babu
Abstract: Diffusion models have become central to various image editing tasks, yet they often fail to fully adhere to physical laws, particularly with effects like shadows, reflections, and occlusions. In this work, we address the challenge of generating photorealistic mirror reflections using diffusion-based generative models. Despite extensive training data, existing diffusion models frequently overlook the nuanced details crucial to authentic mirror reflections. Recent approaches have attempted to resolve this by creating synhetic datasets and framing reflection generation as an inpainting task; however, they struggle to generalize across different object orientations and positions relative to the mirror. Our method overcomes these limitations by introducing key augmentations into the synthetic data pipeline: (1) random object positioning, (2) randomized rotations, and (3) grounding of objects, significantly enhancing generalization across poses and placements. To further address spatial relationships and occlusions in scenes with multiple objects, we implement a strategy to pair objects during dataset generation, resulting in a dataset robust enough to handle these complex scenarios. Achieving generalization to real-world scenes remains a challenge, so we introduce a three-stage training curriculum to develop the MirrorFusion 2.0 model to improve real-world performance. We provide extensive qualitative and quantitative evaluations to support our approach. The project page is available at: https://mirror-verse.github.io/.
Authors: Tajamul Ashraf, Rajes Manna, Partha Sarathi Purkayastha, Tavaheed Tariq, Janibul Bashir
Abstract: We focus on the Source Free Object Detection (SFOD) problem, when source data is unavailable during adaptation, and the model must adapt to the unlabeled target domain. In medical imaging, several approaches have leveraged a semi-supervised student-teacher architecture to bridge domain discrepancy. Context imbalance in labeled training data and significant domain shifts between domains can lead to biased teacher models that produce inaccurate pseudolabels, degrading the student model's performance and causing a mode collapse. Class imbalance, particularly when one class significantly outnumbers another, leads to contextual bias. To tackle the problem of context bias and the significant performance drop of the student model in the SFOD setting, we introduce Grounded Teacher (GT) as a standard framework. In this study, we model contextual relationships using a dedicated relational context module and leverage it to mitigate inherent biases in the model. This approach enables us to apply augmentations to closely related classes, across and within domains, enhancing the performance of underrepresented classes while keeping the effect on dominant classes minimal. We further improve the quality of predictions by implementing an expert foundational branch to supervise the student model. We validate the effectiveness of our approach in mitigating context bias under the SFOD setting through experiments on three medical datasets supported by comprehensive ablation studies. All relevant resources, including preprocessed data, trained model weights, and code, are publicly available at this https://github.com/Tajamul21/Grounded_Teacher.
Authors: David Ma, Yuanxing Zhang, Jincheng Ren, Jarvis Guo, Yifan Yao, Zhenlin Wei, Zhenzhu Yang, Zhongyuan Peng, Boyu Feng, Jun Ma, Xiao Gu, Zhoufutu Wen, King Zhu, Yancheng He, Meng Cao, Shiwen Ni, Jiaheng Liu, Wenhao Huang, Ge Zhang, Xiaojie Jin
Abstract: Existing evaluation frameworks for Multimodal Large Language Models (MLLMs) primarily focus on image reasoning or general video understanding tasks, largely overlooking the significant role of image context in video comprehension. To bridge this gap, we propose IV-Bench, the first comprehensive benchmark for evaluating Image-Grounded Video Perception and Reasoning. IV-Bench consists of 967 videos paired with 2,585 meticulously annotated image-text queries across 13 tasks (7 perception and 6 reasoning tasks) and 5 representative categories. Extensive evaluations of state-of-the-art open-source (e.g., InternVL2.5, Qwen2.5-VL) and closed-source (e.g., GPT-4o, Gemini2-Flash and Gemini2-Pro) MLLMs demonstrate that current models substantially underperform in image-grounded video Perception and Reasoning, merely achieving at most 28.9% accuracy. Further analysis reveals key factors influencing model performance on IV-Bench, including inference pattern, frame number, and resolution. Additionally, through a simple data synthesis approach, we demonstratethe challenges of IV- Bench extend beyond merely aligning the data format in the training proecss. These findings collectively provide valuable insights for future research. Our codes and data are released in https://github.com/multimodal-art-projection/IV-Bench.
URLs: https://github.com/multimodal-art-projection/IV-Bench.
Authors: Jonathan Brokman, Amit Giloni, Omer Hofman, Roman Vainshtein, Hisashi Kojima, Guy Gilboa
Abstract: Distinguishing between real and AI-generated images, commonly referred to as 'image detection', presents a timely and significant challenge. Despite extensive research in the (semi-)supervised regime, zero-shot and few-shot solutions have only recently emerged as promising alternatives. Their main advantage is in alleviating the ongoing data maintenance, which quickly becomes outdated due to advances in generative technologies. We identify two main gaps: (1) a lack of theoretical grounding for the methods, and (2) significant room for performance improvements in zero-shot and few-shot regimes. Our approach is founded on understanding and quantifying the biases inherent in generated content, where we use these quantities as criteria for characterizing generated images. Specifically, we explore the biases of the implicit probability manifold, captured by a pre-trained diffusion model. Through score-function analysis, we approximate the curvature, gradient, and bias towards points on the probability manifold, establishing criteria for detection in the zero-shot regime. We further extend our contribution to the few-shot setting by employing a mixture-of-experts methodology. Empirical results across 20 generative models demonstrate that our method outperforms current approaches in both zero-shot and few-shot settings. This work advances the theoretical understanding and practical usage of generated content biases through the lens of manifold analysis.
Authors: Berk Tinaz, Zalan Fabian, Mahdi Soltanolkotabi
Abstract: Diffusion models have become the go-to method for text-to-image generation, producing high-quality images from noise through a process called reverse diffusion. Understanding the dynamics of the reverse diffusion process is crucial in steering the generation and achieving high sample quality. However, the inner workings of diffusion models is still largely a mystery due to their black-box nature and complex, multi-step generation process. Mechanistic Interpretability (MI) techniques, such as Sparse Autoencoders (SAEs), aim at uncovering the operating principles of models through granular analysis of their internal representations. These MI techniques have been successful in understanding and steering the behavior of large language models at scale. However, the great potential of SAEs has not yet been applied toward gaining insight into the intricate generative process of diffusion models. In this work, we leverage the SAE framework to probe the inner workings of a popular text-to-image diffusion model, and uncover a variety of human-interpretable concepts in its activations. Interestingly, we find that even before the first reverse diffusion step is completed, the final composition of the scene can be predicted surprisingly well by looking at the spatial distribution of activated concepts. Moreover, going beyond correlational analysis, we show that the discovered concepts have a causal effect on the model output and can be leveraged to steer the generative process. We design intervention techniques aimed at manipulating image composition and style, and demonstrate that (1) in early stages of diffusion image composition can be effectively controlled, (2) in the middle stages of diffusion image composition is finalized, however stylistic interventions are effective, and (3) in the final stages of diffusion only minor textural details are subject to change.
Authors: Atin Pothiraj, Elias Stengel-Eskin, Jaemin Cho, Mohit Bansal
Abstract: Recognizing and reasoning about occluded (partially or fully hidden) objects is vital to understanding visual scenes, as occlusions frequently occur in real-world environments and act as obstacles for spatial comprehension. To test models' ability to reason about multiple occluded objects, we introduce a novel task, Counting Amodally for Patterns Through Unseen REgions (CAPTURe), which requires a model to count objects arranged in a pattern by inferring how the pattern continues behind an occluder (an object which blocks parts of the scene). CAPTURe requires both recognizing visual patterns and reasoning, making it a useful testbed for evaluating vision-language models (VLMs) on whether they understand occluded patterns and possess spatial understanding skills. By requiring models to reason about occluded objects, CAPTURe also tests VLMs' ability to form world models that would allow them to fill in missing information. CAPTURe consists of two parts: (1) CAPTURe-real, with manually filtered images of real objects in patterns and (2) CAPTURe-synthetic, a controlled diagnostic with generated patterned images. We evaluate four strong VLMs (GPT-4o, Intern-VL2, Molmo, and Qwen2-VL) on CAPTURe, finding that models struggle to count on both occluded and unoccluded patterns. Crucially, we find that models perform worse with occlusion, suggesting that VLMs are also deficient in inferring unseen spatial relationships: even the strongest VLMs like GPT-4o fail to count with occlusion. In contrast, we find that humans achieve very little error on CAPTURe. We also find that providing auxiliary information of occluded object locations increases performance, underscoring that the model error comes both from an inability to handle occlusion as well as difficulty counting in images.
Authors: Yixuan Zhu, Haolin Wang, Ao Li, Wenliang Zhao, Yansong Tang, Jingxuan Niu, Lei Chen, Jie Zhou, Jiwen Lu
Abstract: Image enhancement finds wide-ranging applications in real-world scenarios due to complex environments and the inherent limitations of imaging devices. Recent diffusion-based methods yield promising outcomes but necessitate prolonged and computationally intensive iterative sampling. In response, we propose InstaRevive, a straightforward yet powerful image enhancement framework that employs score-based diffusion distillation to harness potent generative capability and minimize the sampling steps. To fully exploit the potential of the pre-trained diffusion model, we devise a practical and effective diffusion distillation pipeline using dynamic control to address inaccuracies in updating direction during score matching. Our control strategy enables a dynamic diffusing scope, facilitating precise learning of denoising trajectories within the diffusion model and ensuring accurate distribution matching gradients during training. Additionally, to enrich guidance for the generative power, we incorporate textual prompts via image captioning as auxiliary conditions, fostering further exploration of the diffusion model. Extensive experiments substantiate the efficacy of our framework across a diverse array of challenging tasks and datasets, unveiling the compelling efficacy and efficiency of InstaRevive in delivering high-quality and visually appealing results. Code is available at https://github.com/EternalEvan/InstaRevive.
Authors: Shichen Li, Chenhui Shao
Abstract: Food drying is essential for food production, extending shelf life, and reducing transportation costs. Accurate real-time forecasting of drying readiness is crucial for minimizing energy consumption, improving productivity, and ensuring product quality. However, this remains challenging due to the dynamic nature of drying, limited data availability, and the lack of effective predictive analytical methods. To address this gap, we propose an end-to-end multi-modal data fusion framework that integrates in-situ video data with process parameters for real-time food drying readiness forecasting. Our approach leverages a new encoder-decoder architecture with modality-specific encoders and a transformer-based decoder to effectively extract features while preserving the unique structure of each modality. We apply our approach to sugar cookie drying, where time-to-ready is predicted at each timestamp. Experimental results demonstrate that our model achieves an average prediction error of only 15 seconds, outperforming state-of-the-art data fusion methods by 65.69% and a video-only model by 11.30%. Additionally, our model balances prediction accuracy, model size, and computational efficiency, making it well-suited for heterogenous industrial datasets. The proposed model is extensible to various other industrial modality fusion tasks for online decision-making.
Authors: Yunfeng Li, Bo Wang, Jiahao Wan, Xueyi Wu, Ye Li
Abstract: Underwater observation systems typically integrate optical cameras and imaging sonar systems. When underwater visibility is insufficient, only sonar systems can provide stable data, which necessitates exploration of the underwater acoustic object tracking (UAOT) task. Previous studies have explored traditional methods and Siamese networks for UAOT. However, the absence of a unified evaluation benchmark has significantly constrained the value of these methods. To alleviate this limitation, we propose the first large-scale UAOT benchmark, SonarT165, comprising 165 square sequences, 165 fan sequences, and 205K high-quality annotations. Experimental results demonstrate that SonarT165 reveals limitations in current state-of-the-art SOT trackers. To address these limitations, we propose STFTrack, an efficient framework for acoustic object tracking. It includes two novel modules, a multi-view template fusion module (MTFM) and an optimal trajectory correction module (OTCM). The MTFM module integrates multi-view feature of both the original image and the binary image of the dynamic template, and introduces a cross-attention-like layer to fuse the spatio-temporal target representations. The OTCM module introduces the acoustic-response-equivalent pixel property and proposes normalized pixel brightness response scores, thereby suppressing suboptimal matches caused by inaccurate Kalman filter prediction boxes. To further improve the model feature, STFTrack introduces a acoustic image enhancement method and a Frequency Enhancement Module (FEM) into its tracking pipeline. Comprehensive experiments show the proposed STFTrack achieves state-of-the-art performance on the proposed benchmark. The code is available at https://github.com/LiYunfengLYF/SonarT165.
Authors: Hongxing Peng, Kang Lin, Huanai Liu
Abstract: Hyperspectral image (HSI) classification has been one of the hot topics in remote sensing fields. Recently, the Mamba architecture based on selective state-space models (S6) has demonstrated great advantages in long sequence modeling. However, the unique properties of hyperspectral data, such as high dimensionality and feature inlining, pose challenges to the application of Mamba to HSI classification. To compensate for these shortcomings, we propose an full-field interaction multi-groups Mamba framework (HS-Mamba), which adopts a strategy different from pixel-patch based or whole-image based, but combines the advantages of both. The patches cut from the whole image are sent to multi-groups Mamba, combined with positional information to perceive local inline features in the spatial and spectral domains, and the whole image is sent to a lightweight attention module to enhance the global feature representation ability. Specifically, HS-Mamba consists of a dual-channel spatial-spectral encoder (DCSS-encoder) module and a lightweight global inline attention (LGI-Att) branch. The DCSS-encoder module uses multiple groups of Mamba to decouple and model the local features of dual-channel sequences with non-overlapping patches. The LGI-Att branch uses a lightweight compressed and extended attention module to perceive the global features of the spatial and spectral domains of the unsegmented whole image. By fusing local and global features, high-precision classification of hyperspectral images is achieved. Extensive experiments demonstrate the superiority of the proposed HS-Mamba, outperforming state-of-the-art methods on four benchmark HSI datasets.
Authors: Jinda Lu, Jinghan Li, Yuan Gao, Junkang Wu, Jiancan Wu, Xiang Wang, Xiangnan He
Abstract: Preference alignment through Direct Preference Optimization (DPO) has demonstrated significant effectiveness in aligning multimodal large language models (MLLMs) with human preferences. However, existing methods focus primarily on language preferences while neglecting the critical visual context. In this paper, we propose an Adaptive Vision-enhanced Preference optimization (AdaViP) that addresses these limitations through two key innovations: (1) vision-based preference pair construction, which integrates multiple visual foundation models to strategically remove key visual elements from the image, enhancing MLLMs' sensitivity to visual details; and (2) adaptive preference optimization that dynamically balances vision- and language-based preferences for more accurate alignment. Extensive evaluations across different benchmarks demonstrate our effectiveness. Notably, our AdaViP-7B achieves 93.7% and 96.4% reductions in response-level and mentioned-level hallucination respectively on the Object HalBench, significantly outperforming current state-of-the-art methods.
Authors: Jingzhi Li, Changjiang Luo, Ruoyu Chen, Hua Zhang, Wenqi Ren, Jianhou Gan, Xiaochun Cao
Abstract: Recent advances in multimodal large language models (MLLMs) have demonstrated strong capabilities in understanding general visual content. However, these general-domain MLLMs perform poorly in face perception tasks, often producing inaccurate or misleading responses to face-specific queries. To address this gap, we propose FaceInsight, the versatile face perception MLLM that provides fine-grained facial information. Our approach introduces visual-textual alignment of facial knowledge to model both uncertain dependencies and deterministic relationships among facial information, mitigating the limitations of language-driven reasoning. Additionally, we incorporate face segmentation maps as an auxiliary perceptual modality, enriching the visual input with localized structural cues to enhance semantic understanding. Comprehensive experiments and analyses across three face perception tasks demonstrate that FaceInsight consistently outperforms nine compared MLLMs under both training-free and fine-tuned settings.
Authors: Doanh C. Bui, Hoai Luan Pham, Vu Trung Duong Le, Tuan Hai Vu, Van Duy Tran, Yasuhiko Nakashima
Abstract: Lifelong learning for whole slide images (WSIs) poses the challenge of training a unified model to perform multiple WSI-related tasks, such as cancer subtyping and tumor classification, in a distributed, continual fashion. This is a practical and applicable problem in clinics and hospitals, as WSIs are large, require storage, processing, and transfer time. Training new models whenever new tasks are defined is time-consuming. Recent work has applied regularization- and rehearsal-based methods to this setting. However, the rise of vision-language foundation models that align diagnostic text with pathology images raises the question: are these models alone sufficient for lifelong WSI learning using zero-shot classification, or is further investigation into continual learning strategies needed to improve performance? To our knowledge, this is the first study to compare conventional continual-learning approaches with vision-language zero-shot classification for WSIs. Our source code and experimental results will be available soon.
Authors: Dengyang Jiang, Mengmeng Wang, Teli Ma, Hengzhuang Li, Yong liu, Guang Dai, Lei Zhang
Abstract: Improving the generalization ability of an affordance grounding model to recognize regions for unseen objects and affordance functions is crucial for real-world application. However, current models are still far away from such standards. To address this problem, we introduce AffordanceSAM, an effective approach that extends SAM's generalization capacity to the domain of affordance grounding. For the purpose of thoroughly transferring SAM's robust performance in segmentation to affordance, we initially propose an affordance-adaption module in order to help modify SAM's segmentation output to be adapted to the specific functional regions required for affordance grounding. We concurrently make a coarse-to-fine training recipe to make SAM first be aware of affordance objects and actions coarsely, and then be able to generate affordance heatmaps finely. Both quantitative and qualitative experiments show the strong generalization capacity of our AffordanceSAM, which not only surpasses previous methods under AGD20K benchmark but also shows evidence to handle the task with novel objects and affordance functions.
Authors: Xian Wu, Chang Liu
Abstract: Many existing video inpainting algorithms utilize optical flows to construct the corresponding maps and then propagate pixels from adjacent frames to missing areas by mapping. Despite the effectiveness of the propagation mechanism, they might encounter blurry and inconsistencies when dealing with inaccurate optical flows or large masks. Recently, Diffusion Transformer (DiT) has emerged as a revolutionary technique for video generation tasks. However, pretrained DiT models for video generation all contain a large amount of parameters, which makes it very time consuming to apply to video inpainting tasks. In this paper, we present DiTPainter, an end-to-end video inpainting model based on Diffusion Transformer (DiT). DiTPainter uses an efficient transformer network designed for video inpainting, which is trained from scratch instead of initializing from any large pretrained models. DiTPainter can address videos with arbitrary lengths and can be applied to video decaptioning and video completion tasks with an acceptable time cost. Experiments show that DiTPainter outperforms existing video inpainting algorithms with higher quality and better spatial-temporal consistency.
Authors: Pei Liu, Yisi Luo, Wenzhen Wang, Xiangyong Cao
Abstract: Infrared dim and small target detection presents a significant challenge due to dynamic multi-frame scenarios and weak target signatures in the infrared modality. Traditional low-rank plus sparse models often fail to capture dynamic backgrounds and global spatial-temporal correlations, which results in background leakage or target loss. In this paper, we propose a novel motion-enhanced nonlocal similarity implicit neural representation (INR) framework to address these challenges. We first integrate motion estimation via optical flow to capture subtle target movements, and propose multi-frame fusion to enhance motion saliency. Second, we leverage nonlocal similarity to construct patch tensors with strong low-rank properties, and propose an innovative tensor decomposition-based INR model to represent the nonlocal patch tensor, effectively encoding both the nonlocal low-rankness and spatial-temporal correlations of background through continuous neural representations. An alternating direction method of multipliers is developed for the nonlocal INR model, which enjoys theoretical fixed-point convergence. Experimental results show that our approach robustly separates dim targets from complex infrared backgrounds, outperforming state-of-the-art methods in detection accuracy and robustness.
Authors: Wei Zhuo, Zhiyue Tang, Wufeng Xue, Hao Ding, Linlin Shen
Abstract: Few-shot semantic segmentation has gained increasing interest due to its generalization capability, i.e., segmenting pixels of novel classes requiring only a few annotated images. Prior work has focused on meta-learning for support-query matching, with extensive development in both prototype-based and aggregation-based methods. To address data scarcity, recent approaches have turned to foundation models to enhance representation transferability for novel class segmentation. Among them, a hybrid dual-modal framework including both DINOv2 and SAM has garnered attention due to their complementary capabilities. We wonder "can we build a unified model with knowledge from both foundation models?" To this end, we propose FS-DINO, with only DINOv2's encoder and a lightweight segmenter. The segmenter features a bottleneck adapter, a meta-visual prompt generator based on dense similarities and semantic embeddings, and a decoder. Through coarse-to-fine cross-model distillation, we effectively integrate SAM's knowledge into our lightweight segmenter, which can be further enhanced by 4D correlation mining on support-query pairs. Extensive experiments on COCO-20i, PASCAL-5i, and FSS-1000 demonstrate the effectiveness and superiority of our method.
Authors: Vidi Team, Celong Liu, Chia-Wen Kuo, Dawei Du, Fan Chen, Guang Chen, Jiamin Yuan, Lingxi Zhang, Lu Guo, Lusha Li, Longyin Wen, Qingyu Chen, Rachel Deng, Sijie Zhu, Stuart Siew, Tong Jin, Wei Lu, Wen Zhong, Xiaohui Shen, Xin Gu, Xing Mei, Xueqiong Qu
Abstract: Humans naturally share information with those they are connected to, and video has become one of the dominant mediums for communication and expression on the Internet. To support the creation of high-quality large-scale video content, a modern pipeline requires a comprehensive understanding of both the raw input materials (e.g., the unedited footage captured by cameras) and the editing components (e.g., visual effects). In video editing scenarios, models must process multiple modalities (e.g., vision, audio, text) with strong background knowledge and handle flexible input lengths (e.g., hour-long raw videos), which poses significant challenges for traditional models. In this report, we introduce Vidi, a family of Large Multimodal Models (LMMs) for a wide range of video understand editing scenarios. The first release focuses on temporal retrieval, i.e., identifying the time ranges within the input videos corresponding to a given text query, which plays a critical role in intelligent editing. The model is capable of processing hour-long videos with strong temporal understanding capability, e.g., retrieve time ranges for certain queries. To support a comprehensive evaluation in real-world scenarios, we also present the VUE-TR benchmark, which introduces five key advancements. 1) Video duration: significantly longer than existing temporal retrival datasets, 2) Audio support: includes audio-based queries, 3) Query format: diverse query lengths/formats, 4) Annotation quality: ground-truth time ranges are manually annotated. 5) Evaluation metric: a refined IoU metric to support evaluation over multiple time ranges. Remarkably, Vidi significantly outperforms leading proprietary models, e.g., GPT-4o and Gemini, on the temporal retrieval task, indicating its superiority in video editing scenarios.
Authors: Jun Dong, Wenli Wu, Jintao Cheng, Xiaoyu Tang
Abstract: Despite the remarkable achievements in object detection, the model's accuracy and efficiency still require further improvement under challenging underwater conditions, such as low image quality and limited computational resources. To address this, we propose an Ultra-Light Real-Time Underwater Object Detection framework, You Sense Only Once Beneath (YSOOB). Specifically, we utilize a Multi-Spectrum Wavelet Encoder (MSWE) to perform frequency-domain encoding on the input image, minimizing the semantic loss caused by underwater optical color distortion. Furthermore, we revisit the unique characteristics of even-sized and transposed convolutions, allowing the model to dynamically select and enhance key information during the resampling process, thereby improving its generalization ability. Finally, we eliminate model redundancy through a simple yet effective channel compression and reconstructed large kernel convolution (RLKC) to achieve model lightweight. As a result, forms a high-performance underwater object detector YSOOB with only 1.2 million parameters. Extensive experimental results demonstrate that, with the fewest parameters, YSOOB achieves mAP50 of 83.1% and 82.9% on the URPC2020 and DUO datasets, respectively, comparable to the current SOTA detectors. The inference speed reaches 781.3 FPS and 57.8 FPS on the T4 GPU (TensorRT FP16) and the edge computing device Jetson Xavier NX (TensorRT FP16), surpassing YOLOv12-N by 28.1% and 22.5%, respectively.
Authors: Yannic Neuhaus, Matthias Hein
Abstract: Since data annotation is costly, benchmark datasets often incorporate labels from established image datasets. In this work, we assess the impact of label errors in MSCOCO on the frequently used object hallucination benchmark POPE. We re-annotate the benchmark images and identify an imbalance in annotation errors across different subsets. Evaluating multiple models on the revised labels, which we denote as RePOPE, we observe notable shifts in model rankings, highlighting the impact of label quality. Code and data are available at https://github.com/YanNeu/RePOPE .
Authors: Dasol Jeong, Donggoo Kang, Jiwon Park, Hyebean Lee, Joonki Paik
Abstract: We propose a diffusion-based framework for zero-shot image editing that unifies text-guided and reference-guided approaches without requiring fine-tuning. Our method leverages diffusion inversion and timestep-specific null-text embeddings to preserve the structural integrity of the source image. By introducing a stage-wise latent injection strategy-shape injection in early steps and attribute injection in later steps-we enable precise, fine-grained modifications while maintaining global consistency. Cross-attention with reference latents facilitates semantic alignment between the source and reference. Extensive experiments across expression transfer, texture transformation, and style infusion demonstrate state-of-the-art performance, confirming the method's scalability and adaptability to diverse image editing scenarios.
Authors: Manjunath D, Aniruddh Sikdar, Prajwal Gurunath, Sumanth Udupa, Suresh Sundaram
Abstract: Domain-adaptive thermal object detection plays a key role in facilitating visible (RGB)-to-thermal (IR) adaptation by reducing the need for co-registered image pairs and minimizing reliance on large annotated IR datasets. However, inherent limitations of IR images, such as the lack of color and texture cues, pose challenges for RGB-trained models, leading to increased false positives and poor-quality pseudo-labels. To address this, we propose Semantic-Aware Gray color Augmentation (SAGA), a novel strategy for mitigating color bias and bridging the domain gap by extracting object-level features relevant to IR images. Additionally, to validate the proposed SAGA for drone imagery, we introduce the IndraEye, a multi-sensor (RGB-IR) dataset designed for diverse applications. The dataset contains 5,612 images with 145,666 instances, captured from diverse angles, altitudes, backgrounds, and times of day, offering valuable opportunities for multimodal learning, domain adaptation for object detection and segmentation, and exploration of sensor-specific strengths and weaknesses. IndraEye aims to enhance the development of more robust and accurate aerial perception systems, especially in challenging environments. Experimental results show that SAGA significantly improves RGB-to-IR adaptation for autonomous driving and IndraEye dataset, achieving consistent performance gains of +0.4% to +7.6% (mAP) when integrated with state-of-the-art domain adaptation techniques. The dataset and codes are available at https://github.com/airliisc/IndraEye.
Authors: Menan Velayuthan, Asiri Gawesha, Purushoth Velayuthan, Nuwan Kodagoda, Dharshana Kasthurirathna, Pradeepa Samarasinghe
Abstract: In human-computer interaction, head pose estimation profoundly influences application functionality. Although utilizing facial landmarks is valuable for this purpose, existing landmark-based methods prioritize precision over simplicity and model size, limiting their deployment on edge devices and in compute-poor environments. To bridge this gap, we propose \textbf{Grouped Attention Deep Sets (GADS)}, a novel architecture based on the Deep Set framework. By grouping landmarks into regions and employing small Deep Set layers, we reduce computational complexity. Our multihead attention mechanism extracts and combines inter-group information, resulting in a model that is $7.5\times$ smaller and executes $25\times$ faster than the current lightest state-of-the-art model. Notably, our method achieves an impressive reduction, being $4321\times$ smaller than the best-performing model. We introduce vanilla GADS and Hybrid-GADS (landmarks + RGB) and evaluate our models on three benchmark datasets -- AFLW2000, BIWI, and 300W-LP. We envision our architecture as a robust baseline for resource-constrained head pose estimation methods.
Authors: Qirui Yang, Fangpu Zhang, Yeying Jin, Qihua Cheng, Pengtao Jiang, Huanjing Yue, Jingyu Yang
Abstract: With the rapid advancement of mobile imaging, capturing screens using smartphones has become a prevalent practice in distance learning and conference recording. However, moir\'e artifacts, caused by frequency aliasing between display screens and camera sensors, are further amplified by the image signal processing pipeline, leading to severe visual degradation. Existing sRGB domain demoir\'eing methods struggle with irreversible information loss, while recent two-stage raw domain approaches suffer from information bottlenecks and inference inefficiency. To address these limitations, we propose a single-stage raw domain demoir\'eing framework, Dual-Stream Demoir\'eing Network (DSDNet), which leverages the synergy of raw and YCbCr images to remove moir\'e while preserving luminance and color fidelity. Specifically, to guide luminance correction and moir\'e removal, we design a raw-to-YCbCr mapping pipeline and introduce the Synergic Attention with Dynamic Modulation (SADM) module. This module enriches the raw-to-sRGB conversion with cross-domain contextual features. Furthermore, to better guide color fidelity, we develop a Luminance-Chrominance Adaptive Transformer (LCAT), which decouples luminance and chrominance representations. Extensive experiments demonstrate that DSDNet outperforms state-of-the-art methods in both visual quality and quantitative evaluation, and achieves an inference speed $\mathrm{\textbf{2.4x}}$ faster than the second-best method, highlighting its practical advantages. We provide an anonymous online demo at https://xxxxxxxxdsdnet.github.io/DSDNet/.
Authors: Lei Xu, Mehmet Yamac, Mete Ahishali, Moncef Gabbouj
Abstract: Edge detection has attracted considerable attention thanks to its exceptional ability to enhance performance in downstream computer vision tasks. In recent years, various deep learning methods have been explored for edge detection tasks resulting in a significant performance improvement compared to conventional computer vision algorithms. In neural networks, edge detection tasks require considerably large receptive fields to provide satisfactory performance. In a typical convolutional operation, such a large receptive field can be achieved by utilizing a significant number of consecutive layers, which yields deep network structures. Recently, a Multi-scale Tensorial Summation (MTS) factorization operator was presented, which can achieve very large receptive fields even from the initial layers. In this paper, we propose a novel MTS Dimensional Reduction (MTS-DR) module guided neural network, MTS-DR-Net, for the edge detection task. The MTS-DR-Net uses MTS layers, and corresponding MTS-DR blocks as a new backbone to remove redundant information initially. Such a dimensional reduction module enables the neural network to focus specifically on relevant information (i.e., necessary subspaces). Finally, a weight U-shaped refinement module follows MTS-DR blocks in the MTS-DR-Net. We conducted extensive experiments on two benchmark edge detection datasets: BSDS500 and BIPEDv2 to verify the effectiveness of our model. The implementation of the proposed MTS-DR-Net can be found at https://github.com/LeiXuAI/MTS-DR-Net.git.
Authors: Quentin Herau, Nathan Piasco, Moussab Bennehar, Luis Rolado, Dzmitry Tsishkou, Bingbing Liu, Cyrille Migniot, Pascal Vasseur, C\'edric Demonceaux
Abstract: Autonomous driving systems rely on accurate perception and localization of the ego car to ensure safety and reliability in challenging real-world driving scenarios. Public datasets play a vital role in benchmarking and guiding advancement in research by providing standardized resources for model development and evaluation. However, potential inaccuracies in sensor calibration and vehicle poses within these datasets can lead to erroneous evaluations of downstream tasks, adversely impacting the reliability and performance of the autonomous systems. To address this challenge, we propose a robust optimization method based on Neural Radiance Fields (NeRF) to refine sensor poses and calibration parameters, enhancing the integrity of dataset benchmarks. To validate improvement in accuracy of our optimized poses without ground truth, we present a thorough evaluation process, relying on reprojection metrics, Novel View Synthesis rendering quality, and geometric alignment. We demonstrate that our method achieves significant improvements in sensor pose accuracy. By optimizing these critical parameters, our approach not only improves the utility of existing datasets but also paves the way for more reliable autonomous driving models. To foster continued progress in this field, we make the optimized sensor poses publicly available, providing a valuable resource for the research community.
Authors: Daniele Baieri, Riccardo Cicciarella, Michael Kr\"utzen, Emanuele Rodol\`a, Silvia Zuffi
Abstract: We address the problem of estimating the metric 3D shape and motion of wild dolphins from monocular video, with the aim of assessing their body condition. While considerable progress has been made in reconstructing 3D models of terrestrial quadrupeds, aquatic animals remain unexplored due to the difficulty of observing them in their natural underwater environment. To address this, we propose a model-based approach that incorporates a transmission model to account for water-induced occlusion. We apply our method to video captured under different sea conditions. We estimate mass and volume, and compare our results to a manual 2D measurements-based method.
Authors: Johan \"Ofverstedt, Elin Lundstr\"om, H{\aa}kan Ahlstr\"om, Joel Kullberg
Abstract: Age prediction from medical images or other health-related non-imaging data is an important approach to data-driven aging research, providing knowledge of how much information a specific tissue or organ carries about the chronological age of the individual. In this work, we studied the prediction of age from computed tomography angiography (CTA) images, which provide detailed representations of the heart morphology, with the goals of (i) studying the relationship between morphology and aging, and (ii) developing a novel \emph{morphological heart age} biomarker. We applied an image registration-based method that standardizes the images from the whole cohort into a single space. We then extracted supervoxels (using unsupervised segmentation), and corresponding robust features of density and local volume, which provide a detailed representation of the heart morphology while being robust to registration errors. Machine learning models are then trained to fit regression models from these features to the chronological age. We applied the method to a subset of the images from the Swedish CArdioPulomonary bioImage Study (SCAPIS) dataset, consisting of 721 females and 666 males. We observe a mean absolute error of $2.74$ years for females and $2.77$ years for males. The predictions from different sub-regions of interest were observed to be more highly correlated with the predictions from the whole heart, compared to the chronological age, revealing a high consistency in the predictions from morphology. Saliency analysis was also performed on the prediction models to study what regions are associated positively and negatively with the predicted age. This resulted in detailed association maps where the density and volume of known, as well as some novel sub-regions of interest, are determined to be important. The saliency analysis aids in the interpretability of the models and their predictions.
Authors: Ningli Xu, Rongjun Qin
Abstract: Generating consistent ground-view images from satellite imagery is challenging, primarily due to the large discrepancies in viewing angles and resolution between satellite and ground-level domains. Previous efforts mainly concentrated on single-view generation, often resulting in inconsistencies across neighboring ground views. In this work, we propose a novel cross-view synthesis approach designed to overcome these challenges by ensuring consistency across ground-view images generated from satellite views. Our method, based on a fixed latent diffusion model, introduces two conditioning modules: satellite-guided denoising, which extracts high-level scene layout to guide the denoising process, and satellite-temporal denoising, which captures camera motion to maintain consistency across multiple generated views. We further contribute a large-scale satellite-ground dataset containing over 100,000 perspective pairs to facilitate extensive ground scene or video generation. Experimental results demonstrate that our approach outperforms existing methods on perceptual and temporal metrics, achieving high photorealism and consistency in multi-view outputs.
Authors: Dinh Nam Pham, Torsten Rahne
Abstract: When reading lips, many people benefit from additional visual information from the lip movements of the speaker, which is, however, very error prone. Algorithms for lip reading with artificial intelligence based on artificial neural networks significantly improve word recognition but are not available for the German language. A total of 1806 video clips with only one German-speaking person each were selected, split into word segments, and assigned to word classes using speech-recognition software. In 38,391 video segments with 32 speakers, 18 polysyllabic, visually distinguishable words were used to train and validate a neural network. The 3D Convolutional Neural Network and Gated Recurrent Units models and a combination of both models (GRUConv) were compared, as were different image sections and color spaces of the videos. The accuracy was determined in 5000 training epochs. Comparison of the color spaces did not reveal any relevant different correct classification rates in the range from 69% to 72%. With a cut to the lips, a significantly higher accuracy of 70% was achieved than when cut to the entire speaker's face (34%). With the GRUConv model, the maximum accuracies were 87% with known speakers and 63% in the validation with unknown speakers. The neural network for lip reading, which was first developed for the German language, shows a very high level of accuracy, comparable to English-language algorithms. It works with unknown speakers as well and can be generalized with more word classes.
Authors: Jiaqi Tang, Yinsong Xu, Qingchao Chen
Abstract: Object classification models utilizing point cloud data are fundamental for 3D media understanding, yet they often struggle with unseen or out-of-distribution (OOD) scenarios. Existing point cloud unsupervised domain adaptation (UDA) methods typically employ a multi-task learning (MTL) framework that combines primary classification tasks with auxiliary self-supervision tasks to bridge the gap between cross-domain feature distributions. However, our further experiments demonstrate that not all gradients from self-supervision tasks are beneficial and some may negatively impact the classification performance. In this paper, we propose a novel solution, termed Saliency Map-based Data Sampling Block (SM-DSB), to mitigate these gradient conflicts. Specifically, our method designs a new scoring mechanism based on the skewness of 3D saliency maps to estimate gradient conflicts without requiring target labels. Leveraging this, we develop a sample selection strategy that dynamically filters out samples whose self-supervision gradients are not beneficial for the classification. Our approach is scalable, introducing modest computational overhead, and can be integrated into all the point cloud UDA MTL frameworks. Extensive evaluations demonstrate that our method outperforms state-of-the-art approaches. In addition, we provide a new perspective on understanding the UDA problem through back-propagation analysis.
Authors: Songyan Xie, Jinghang Wen, Encheng Su, Qiucheng Yu
Abstract: Near-infrared (NIR) face recognition systems, which can operate effectively in low-light conditions or in the presence of makeup, exhibit vulnerabilities when subjected to physical adversarial attacks. To further demonstrate the potential risks in real-world applications, we design a novel, stealthy, and practical adversarial patch to attack NIR face recognition systems in a black-box setting. We achieved this by utilizing human-imperceptible infrared-absorbing ink to generate multiple patches with digitally optimized shapes and positions for infrared images. To address the optimization mismatch between digital and real-world NIR imaging, we develop a light reflection model for human skin to minimize pixel-level discrepancies by simulating NIR light reflection. Compared to state-of-the-art (SOTA) physical attacks on NIR face recognition systems, the experimental results show that our method improves the attack success rate in both digital and physical domains, particularly maintaining effectiveness across various face postures. Notably, the proposed approach outperforms SOTA methods, achieving an average attack success rate of 82.46% in the physical domain across different models, compared to 64.18% for existing methods. The artifact is available at https://anonymous.4open.science/r/Human-imperceptible-adversarial-patch-0703/.
URLs: https://anonymous.4open.science/r/Human-imperceptible-adversarial-patch-0703/.
Authors: Yiqian Wu, Malte Prinzler, Xiaogang Jin, Siyu Tang
Abstract: The generation of high-quality, animatable 3D head avatars from text has enormous potential in content creation applications such as games, movies, and embodied virtual assistants. Current text-to-3D generation methods typically combine parametric head models with 2D diffusion models using score distillation sampling to produce 3D-consistent results. However, they struggle to synthesize realistic details and suffer from misalignments between the appearance and the driving parametric model, resulting in unnatural animation results. We discovered that these limitations stem from ambiguities in the 2D diffusion predictions during 3D avatar distillation, specifically: i) the avatar's appearance and geometry is underconstrained by the text input, and ii) the semantic alignment between the predictions and the parametric head model is insufficient because the diffusion model alone cannot incorporate information from the parametric model. In this work, we propose a novel framework, AnimPortrait3D, for text-based realistic animatable 3DGS avatar generation with morphable model alignment, and introduce two key strategies to address these challenges. First, we tackle appearance and geometry ambiguities by utilizing prior information from a pretrained text-to-3D model to initialize a 3D avatar with robust appearance, geometry, and rigging relationships to the morphable model. Second, we refine the initial 3D avatar for dynamic expressions using a ControlNet that is conditioned on semantic and normal maps of the morphable model to ensure accurate alignment. As a result, our method outperforms existing approaches in terms of synthesis quality, alignment, and animation fidelity. Our experiments show that the proposed method advances the state of the art in text-based, animatable 3D head avatar generation.
Authors: Diego de Oliveira Hitzges, Suman Ghosh, Guillermo Gallego
Abstract: Event cameras offer a promising avenue for multi-view stereo depth estimation and Simultaneous Localization And Mapping (SLAM) due to their ability to detect blur-free 3D edges at high-speed and over broad illumination conditions. However, traditional deep learning frameworks designed for conventional cameras struggle with the asynchronous, stream-like nature of event data, as their architectures are optimized for discrete, image-like inputs. We propose a scalable, flexible and adaptable framework for pixel-wise depth estimation with event cameras in both monocular and stereo setups. The 3D scene structure is encoded into disparity space images (DSIs), representing spatial densities of rays obtained by back-projecting events into space via known camera poses. Our neural network processes local subregions of the DSIs combining 3D convolutions and a recurrent structure to recognize valuable patterns for depth prediction. Local processing enables fast inference with full parallelization and ensures constant ultra-low model complexity and memory costs, regardless of camera resolution. Experiments on standard benchmarks (MVSEC and DSEC datasets) demonstrate unprecedented effectiveness: (i) using purely monocular data, our method achieves comparable results to existing stereo methods; (ii) when applied to stereo data, it strongly outperforms all state-of-the-art (SOTA) approaches, reducing the mean absolute error by at least 42%; (iii) our method also allows for increases in depth completeness by more than 3-fold while still yielding a reduction in median absolute error of at least 30%. Given its remarkable performance and effective processing of event-data, our framework holds strong potential to become a standard approach for using deep learning for event-based depth estimation and SLAM. Project page: https://github.com/tub-rip/DERD-Net
Authors: Lotfi Abdelkrim Mecharbat, Ibrahim Elmakky, Martin Takac, Mohammed Yaqub
Abstract: Deep learning (DL) has achieved remarkable progress in the field of medical imaging. However, adapting DL models to medical tasks remains a significant challenge, primarily due to two key factors: (1) architecture selection, as different tasks necessitate specialized model designs, and (2) weight initialization, which directly impacts the convergence speed and final performance of the models. Although transfer learning from ImageNet is a widely adopted strategy, its effectiveness is constrained by the substantial differences between natural and medical images. To address these challenges, we introduce Medical Neural Network Search (MedNNS), the first Neural Network Search framework for medical imaging applications. MedNNS jointly optimizes architecture selection and weight initialization by constructing a meta-space that encodes datasets and models based on how well they perform together. We build this space using a Supernetwork-based approach, expanding the model zoo size by 51x times over previous state-of-the-art (SOTA) methods. Moreover, we introduce rank loss and Fr\'echet Inception Distance (FID) loss into the construction of the space to capture inter-model and inter-dataset relationships, thereby achieving more accurate alignment in the meta-space. Experimental results across multiple datasets demonstrate that MedNNS significantly outperforms both ImageNet pre-trained DL models and SOTA Neural Architecture Search (NAS) methods, achieving an average accuracy improvement of 1.7% across datasets while converging substantially faster. The code and the processed meta-space is available at https://github.com/BioMedIA-MBZUAI/MedNNS.
Authors: Farida Mohsen, Samir Belhaouari, Zubair Shah
Abstract: Diabetic retinopathy is a serious ocular complication that poses a significant threat to patients' vision and overall health. Early detection and accurate grading are essential to prevent vision loss. Current automatic grading methods rely heavily on deep learning applied to retinal fundus images, but the complex, irregular patterns of lesions in these images, which vary in shape and distribution, make it difficult to capture subtle changes. This study introduces RadFuse, a multi-representation deep learning framework that integrates non-linear RadEx-transformed sinogram images with traditional fundus images to enhance diabetic retinopathy detection and grading. Our RadEx transformation, an optimized non-linear extension of the Radon transform, generates sinogram representations to capture complex retinal lesion patterns. By leveraging both spatial and transformed domain information, RadFuse enriches the feature set available to deep learning models, improving the differentiation of severity levels. We conducted extensive experiments on two benchmark datasets, APTOS-2019 and DDR, using three convolutional neural networks (CNNs): ResNeXt-50, MobileNetV2, and VGG19. RadFuse showed significant improvements over fundus-image-only models across all three CNN architectures and outperformed state-of-the-art methods on both datasets. For severity grading across five stages, RadFuse achieved a quadratic weighted kappa of 93.24%, an accuracy of 87.07%, and an F1-score of 87.17%. In binary classification between healthy and diabetic retinopathy cases, the method reached an accuracy of 99.09%, precision of 98.58%, and recall of 99.6%, surpassing previously established models. These results demonstrate RadFuse's capacity to capture complex non-linear features, advancing diabetic retinopathy classification and promoting the integration of advanced mathematical transforms in medical image analysis.
Authors: Zhiqiang Wei, Lianqing Zheng, Jianan Liu, Tao Huang, Qing-Long Han, Wenwen Zhang, Fengdeng Zhang
Abstract: Accurate 3D semantic occupancy perception is essential for autonomous driving in complex environments with diverse and irregular objects. While vision-centric methods suffer from geometric inaccuracies, LiDAR-based approaches often lack rich semantic information. To address these limitations, MS-Occ, a novel multi-stage LiDAR-camera fusion framework which includes middle-stage fusion and late-stage fusion, is proposed, integrating LiDAR's geometric fidelity with camera-based semantic richness via hierarchical cross-modal fusion. The framework introduces innovations at two critical stages: (1) In the middle-stage feature fusion, the Gaussian-Geo module leverages Gaussian kernel rendering on sparse LiDAR depth maps to enhance 2D image features with dense geometric priors, and the Semantic-Aware module enriches LiDAR voxels with semantic context via deformable cross-attention; (2) In the late-stage voxel fusion, the Adaptive Fusion (AF) module dynamically balances voxel features across modalities, while the High Classification Confidence Voxel Fusion (HCCVF) module resolves semantic inconsistencies using self-attention-based refinement. Experiments on the nuScenes-OpenOccupancy benchmark show that MS-Occ achieves an Intersection over Union (IoU) of 32.1% and a mean IoU (mIoU) of 25.3%, surpassing the state-of-the-art by +0.7% IoU and +2.4% mIoU. Ablation studies further validate the contribution of each module, with substantial improvements in small-object perception, demonstrating the practical value of MS-Occ for safety-critical autonomous driving scenarios.
Authors: Chang Zong, Bin Li, Shoujun Zhou, Jian Wan, Lei Zhang
Abstract: Locating specific segments within an instructional video is an efficient way to acquire guiding knowledge. Generally, the task of obtaining video segments for both verbal explanations and visual demonstrations is known as visual answer localization (VAL). However, users often need multiple interactions to obtain answers that align with their expectations when using the system. During these interactions, humans deepen their understanding of the video content by asking themselves questions, thereby accurately identifying the location. Therefore, we propose a new task, named In-VAL, to simulate the multiple interactions between humans and videos in the procedure of obtaining visual answers. The In-VAL task requires interactively addressing several semantic gap issues, including 1) the ambiguity of user intent in the input questions, 2) the incompleteness of language in video subtitles, and 3) the fragmentation of content in video segments. To address these issues, we propose Ask2Loc, a framework for resolving In-VAL by asking questions. It includes three key modules: 1) a chatting module to refine initial questions and uncover clear intentions, 2) a rewriting module to generate fluent language and create complete descriptions, and 3) a searching module to broaden local context and provide integrated content. We conduct extensive experiments on three reconstructed In-VAL datasets. Compared to traditional end-to-end and two-stage methods, our proposed Ask2Loc can improve performance by up to 14.91 (mIoU) on the In-VAL task. Our code and datasets can be accessed at https://github.com/changzong/Ask2Loc.
Authors: Jian Hu, Dimitrios Korkinof, Shaogang Gong, Mariano Beguerisse-Diaz
Abstract: We introduce ViSMap: Unsupervised Video Summarisation by Meta Prompting, a system to summarise hour long videos with no-supervision. Most existing video understanding models work well on short videos of pre-segmented events, yet they struggle to summarise longer videos where relevant events are sparsely distributed and not pre-segmented. Moreover, long-form video understanding often relies on supervised hierarchical training that needs extensive annotations which are costly, slow and prone to inconsistency. With ViSMaP we bridge the gap between short videos (where annotated data is plentiful) and long ones (where it's not). We rely on LLMs to create optimised pseudo-summaries of long videos using segment descriptions from short ones. These pseudo-summaries are used as training data for a model that generates long-form video summaries, bypassing the need for expensive annotations of long videos. Specifically, we adopt a meta-prompting strategy to iteratively generate and refine creating pseudo-summaries of long videos. The strategy leverages short clip descriptions obtained from a supervised short video model to guide the summary. Each iteration uses three LLMs working in sequence: one to generate the pseudo-summary from clip descriptions, another to evaluate it, and a third to optimise the prompt of the generator. This iteration is necessary because the quality of the pseudo-summaries is highly dependent on the generator prompt, and varies widely among videos. We evaluate our summaries extensively on multiple datasets; our results show that ViSMaP achieves performance comparable to fully supervised state-of-the-art models while generalising across domains without sacrificing performance. Code will be released upon publication.
Authors: Meng Wang, Tian Lin, Qingshan Hou, Aidi Lin, Jingcheng Wang, Qingsheng Peng, Truong X. Nguyen, Danqi Fang, Ke Zou, Ting Xu, Cancan Xue, Ten Cheer Quek, Qinkai Yu, Minxin Liu, Hui Zhou, Zixuan Xiao, Guiqin He, Huiyu Liang, Tingkun Shi, Man Chen, Linna Liu, Yuanyuan Peng, Lianyu Wang, Qiuming Hu, Junhong Chen, Zhenhua Zhang, Cheng Chen, Yitian Zhao, Dianbo Liu, Jianhua Wu, Xinjian Chen, Changqing Zhang, Triet Thanh Nguyen, Yanda Meng, Yalin Zheng, Yih Chung Tham, Carol Y. Cheung, Huazhu Fu, Haoyu Chen, Ching-Yu Cheng
Abstract: Artificial intelligence (AI) shows remarkable potential in medical imaging diagnostics, but current models typically require retraining when deployed across different clinical centers, limiting their widespread adoption. We introduce GlobeReady, a clinician-friendly AI platform that enables ocular disease diagnosis without retraining/fine-tuning or technical expertise. GlobeReady achieves high accuracy across imaging modalities: 93.9-98.5% for an 11-category fundus photo dataset and 87.2-92.7% for a 15-category OCT dataset. Through training-free local feature augmentation, it addresses domain shifts across centers and populations, reaching an average accuracy of 88.9% across five centers in China, 86.3% in Vietnam, and 90.2% in the UK. The built-in confidence-quantifiable diagnostic approach further boosted accuracy to 94.9-99.4% (fundus) and 88.2-96.2% (OCT), while identifying out-of-distribution cases at 86.3% (49 CFP categories) and 90.6% (13 OCT categories). Clinicians from multiple countries rated GlobeReady highly (average 4.6 out of 5) for its usability and clinical relevance. These results demonstrate GlobeReady's robust, scalable diagnostic capability and potential to support ophthalmic care without technical barriers.
Authors: Saban Ozturk, Melih B. Yilmaz, Muti Kara, M. Talat Yavuz, Aykut Ko\c{c}, Tolga \c{C}ukur
Abstract: Diagnostic imaging relies on interpreting both images and radiology reports, but the growing data volumes place significant pressure on medical experts, yielding increased errors and workflow backlogs. Medical vision-language models (med-VLMs) have emerged as a powerful framework to efficiently process multimodal imaging data, particularly in chest X-ray (CXR) evaluations, albeit their performance hinges on how well image and text representations are aligned. Existing alignment methods, predominantly based on contrastive learning, prioritize separation between disease classes over segregation of fine-grained pathology attributes like location, size or severity, leading to suboptimal representations. Here, we propose MedTrim (Meta-entity-driven Triplet mining), a novel method that enhances image-text alignment through multimodal triplet learning synergistically guided by disease class as well as adjectival and directional pathology descriptors. Unlike common alignment methods that separate broad disease classes, MedTrim leverages structured meta-entity information to preserve subtle but clinically significant intra-class variations. For this purpose, we first introduce an ontology-based entity recognition module that extracts pathology-specific meta-entities from CXR reports, as annotations on pathology attributes are rare in public datasets. For refined sample selection in triplet mining, we then introduce a novel score function that captures an aggregate measure of inter-sample similarity based on disease classes and adjectival/directional descriptors. Lastly, we introduce a multimodal triplet alignment objective for explicit within- and cross-modal alignment between samples sharing detailed pathology characteristics. Our demonstrations indicate that MedTrim improves performance in downstream retrieval and classification tasks compared to state-of-the-art alignment methods.
Authors: Ekaterina Kondrateva, Sandzhi Barg, Mikhail Vasiliev
Abstract: Accurate and reproducible brain morphometry from structural MRI is critical for monitoring neuroanatomical changes across time and across imaging domains. Although deep learning has accelerated segmentation workflows, scanner-induced variability and reproducibility limitations remain-especially in longitudinal and multi-site settings. In this study, we benchmark two modern segmentation pipelines, FastSurfer and SynthSeg, both integrated into FreeSurfer, one of the most widely adopted tools in neuroimaging. Using two complementary datasets - a 17-year longitudinal cohort (SIMON) and a 9-site test-retest cohort (SRPBS)-we quantify inter-scan segmentation variability using Dice coefficient, Surface Dice, Hausdorff Distance (HD95), and Mean Absolute Percentage Error (MAPE). Our results reveal up to 7-8% volume variation in small subcortical structures such as the amygdala and ventral diencephalon, even under controlled test-retest conditions. This raises a key question: is it feasible to detect subtle longitudinal changes on the order of 5-10% in pea-sized brain regions, given the magnitude of domain-induced morphometric noise? We further analyze the effects of registration templates and interpolation modes, and propose surface-based quality filtering to improve segmentation reliability. This study provides a reproducible benchmark for morphometric reproducibility and emphasizes the need for harmonization strategies in real-world neuroimaging studies. Code and figures: https://github.com/kondratevakate/brain-mri-segmentation
URLs: https://github.com/kondratevakate/brain-mri-segmentation
Authors: Wang Lin, Liyu Jia, Wentao Hu, Kaihang Pan, Zhongqi Yue, Wei Zhao, Jingyuan Chen, Fei Wu, Hanwang Zhang
Abstract: Despite recent progress in video generation, producing videos that adhere to physical laws remains a significant challenge. Traditional diffusion-based methods struggle to extrapolate to unseen physical conditions (eg, velocity) due to their reliance on data-driven approximations. To address this, we propose to integrate symbolic reasoning and reinforcement learning to enforce physical consistency in video generation. We first introduce the Diffusion Timestep Tokenizer (DDT), which learns discrete, recursive visual tokens by recovering visual attributes lost during the diffusion process. The recursive visual tokens enable symbolic reasoning by a large language model. Based on it, we propose the Phys-AR framework, which consists of two stages: The first stage uses supervised fine-tuning to transfer symbolic knowledge, while the second stage applies reinforcement learning to optimize the model's reasoning abilities through reward functions based on physical conditions. Our approach allows the model to dynamically adjust and improve the physical properties of generated videos, ensuring adherence to physical laws. Experimental results demonstrate that PhysAR can generate videos that are physically consistent.
Authors: Zebin Yao, Lei Ren, Huixing Jiang, Chen Wei, Xiaojie Wang, Ruifan Li, Fangxiang Feng
Abstract: Subject-driven image generation aims to synthesize novel scenes that faithfully preserve subject identity from reference images while adhering to textual guidance, yet existing methods struggle with a critical trade-off between fidelity and efficiency. Tuning-based approaches rely on time-consuming and resource-intensive subject-specific optimization, while zero-shot methods fail to maintain adequate subject consistency. In this work, we propose FreeGraftor, a training-free framework that addresses these limitations through cross-image feature grafting. Specifically, FreeGraftor employs semantic matching and position-constrained attention fusion to transfer visual details from reference subjects to the generated image. Additionally, our framework incorporates a novel noise initialization strategy to preserve geometry priors of reference subjects for robust feature matching. Extensive qualitative and quantitative experiments demonstrate that our method enables precise subject identity transfer while maintaining text-aligned scene synthesis. Without requiring model fine-tuning or additional training, FreeGraftor significantly outperforms existing zero-shot and training-free approaches in both subject fidelity and text alignment. Furthermore, our framework can seamlessly extend to multi-subject generation, making it practical for real-world deployment. Our code is available at https://github.com/Nihukat/FreeGraftor.
Authors: Leonardo Olivi, Edoardo Santero Mormile, Enzo Tartaglione
Abstract: In recent years, the application of Deep Learning techniques has shown remarkable success in various computer vision tasks, paving the way for their deployment in extraterrestrial exploration. Transfer learning has emerged as a powerful strategy for addressing the scarcity of labeled data in these novel environments. This paper represents one of the first efforts in evaluating the feasibility of employing adapters toward efficient transfer learning for rock segmentation in extraterrestrial landscapes, mainly focusing on lunar and martian terrains. Our work suggests that the use of adapters, strategically integrated into a pre-trained backbone model, can be successful in reducing both bandwidth and memory requirements for the target extraterrestrial device. In this study, we considered two memory-saving strategies: layer fusion (to reduce to zero the inference overhead) and an ``adapter ranking'' (to also reduce the transmission cost). Finally, we evaluate these results in terms of task performance, memory, and computation on embedded devices, evidencing trade-offs that open the road to more research in the field.
Authors: Yachun Mi, Yu Li, Weicheng Meng, Chaofeng Chen, Chen Hui, Shaohui Liu
Abstract: The rapid growth of long-duration, high-definition videos has made efficient video quality assessment (VQA) a critical challenge. Existing research typically tackles this problem through two main strategies: reducing model parameters and resampling inputs. However, light-weight Convolution Neural Networks (CNN) and Transformers often struggle to balance efficiency with high performance due to the requirement of long-range modeling capabilities. Recently, the state-space model, particularly Mamba, has emerged as a promising alternative, offering linear complexity with respect to sequence length. Meanwhile, efficient VQA heavily depends on resampling long sequences to minimize computational costs, yet current resampling methods are often weak in preserving essential semantic information. In this work, we present MVQA, a Mamba-based model designed for efficient VQA along with a novel Unified Semantic and Distortion Sampling (USDS) approach. USDS combines semantic patch sampling from low-resolution videos and distortion patch sampling from original-resolution videos. The former captures semantically dense regions, while the latter retains critical distortion details. To prevent computation increase from dual inputs, we propose a fusion mechanism using pre-defined masks, enabling a unified sampling strategy that captures both semantic and quality information without additional computational burden. Experiments show that the proposed MVQA, equipped with USDS, achieve comparable performance to state-of-the-art methods while being $2\times$ as fast and requiring only $1/5$ GPU memory.
Authors: Xinyuan Song, Yangfan He, Sida Li, Jianhui Wang, Hongyang He, Xinhang Yuan, Ruoyu Wang, Jiaqi Chen, Keqin Li, Kuan Lu, Menghao Huo, Binxu Li, Pei Liu
Abstract: Adapter-based methods are commonly used to enhance model performance with minimal additional complexity, especially in video editing tasks that require frame-to-frame consistency. By inserting small, learnable modules into pretrained diffusion models, these adapters can maintain temporal coherence without extensive retraining. Approaches that incorporate prompt learning with both shared and frame-specific tokens are particularly effective in preserving continuity across frames at low training cost. In this work, we want to provide a general theoretical framework for adapters that maintain frame consistency in DDIM-based models under a temporal consistency loss. First, we prove that the temporal consistency objective is differentiable under bounded feature norms, and we establish a Lipschitz bound on its gradient. Second, we show that gradient descent on this objective decreases the loss monotonically and converges to a local minimum if the learning rate is within an appropriate range. Finally, we analyze the stability of modules in the DDIM inversion procedure, showing that the associated error remains controlled. These theoretical findings will reinforce the reliability of diffusion-based video editing methods that rely on adapter strategies and provide theoretical insights in video generation tasks.
Authors: Song Wang, Xiaolu Liu, Lingdong Kong, Jianyun Xu, Chunyong Hu, Gongfan Fang, Wentong Li, Jianke Zhu, Xinchao Wang
Abstract: Self-supervised representation learning for point cloud has demonstrated effectiveness in improving pre-trained model performance across diverse tasks. However, as pre-trained models grow in complexity, fully fine-tuning them for downstream applications demands substantial computational and storage resources. Parameter-efficient fine-tuning (PEFT) methods offer a promising solution to mitigate these resource requirements, yet most current approaches rely on complex adapter and prompt mechanisms that increase tunable parameters. In this paper, we propose PointLoRA, a simple yet effective method that combines low-rank adaptation (LoRA) with multi-scale token selection to efficiently fine-tune point cloud models. Our approach embeds LoRA layers within the most parameter-intensive components of point cloud transformers, reducing the need for tunable parameters while enhancing global feature capture. Additionally, multi-scale token selection extracts critical local information to serve as prompts for downstream fine-tuning, effectively complementing the global context captured by LoRA. The experimental results across various pre-trained models and three challenging public datasets demonstrate that our approach achieves competitive performance with only 3.43% of the trainable parameters, making it highly effective for resource-constrained applications. Source code is available at: https://github.com/songw-zju/PointLoRA.
Authors: Joya Chen, Ziyun Zeng, Yiqi Lin, Wei Li, Zejun Ma, Mike Zheng Shou
Abstract: Recent video large language models (Video LLMs) often depend on costly human annotations or proprietary model APIs (e.g., GPT-4o) to produce training data, which limits their training at scale. In this paper, we explore large-scale training for Video LLM with cheap automatic speech recognition (ASR) transcripts. Specifically, we propose a novel streaming training approach that densely interleaves the ASR words and video frames according to their timestamps. Compared to previous studies in vision-language representation with ASR, our method naturally fits the streaming characteristics of ASR, thus enabling the model to learn temporally-aligned, fine-grained vision-language modeling. To support the training algorithm, we introduce a data production pipeline to process YouTube videos and their closed captions (CC, same as ASR), resulting in Live-CC-5M dataset for pre-training and Live-WhisperX-526K dataset for high-quality supervised fine-tuning (SFT). Remarkably, even without SFT, the ASR-only pre-trained LiveCC-7B-Base model demonstrates competitive general video QA performance and exhibits a new capability in real-time video commentary. To evaluate this, we carefully design a new LiveSports-3K benchmark, using LLM-as-a-judge to measure the free-form commentary. Experiments show our final LiveCC-7B-Instruct model can surpass advanced 72B models (Qwen2.5-VL-72B-Instruct, LLaVA-Video-72B) in commentary quality even working in a real-time mode. Meanwhile, it achieves state-of-the-art results at the 7B/8B scale on popular video QA benchmarks such as VideoMME and OVOBench, demonstrating the broad generalizability of our approach. All resources of this paper have been released at https://showlab.github.io/livecc.
Authors: Frank Li, Hari Trivedi, Bardia Khosravi, Theo Dapamede, Mohammadreza Chavoshi, Abdulhameed Dere, Rohan Satya Isaac, Aawez Mansuri, Janice Newsome, Saptarshi Purkayastha, Judy Gichoya
Abstract: Foundation models, trained on vast amounts of data using self-supervised techniques, have emerged as a promising frontier for advancing artificial intelligence (AI) applications in medicine. This study evaluates three different vision-language foundation models (RAD-DINO, CheXagent, and BiomedCLIP) on their ability to capture fine-grained imaging features for radiology tasks. The models were assessed across classification, segmentation, and regression tasks for pneumothorax and cardiomegaly on chest radiographs. Self-supervised RAD-DINO consistently excelled in segmentation tasks, while text-supervised CheXagent demonstrated superior classification performance. BiomedCLIP showed inconsistent performance across tasks. A custom segmentation model that integrates global and local features substantially improved performance for all foundation models, particularly for challenging pneumothorax segmentation. The findings highlight that pre-training methodology significantly influences model performance on specific downstream tasks. For fine-grained segmentation tasks, models trained without text supervision performed better, while text-supervised models offered advantages in classification and interpretability. These insights provide guidance for selecting foundation models based on specific clinical applications in radiology.
Authors: Sangeet Khemlani, Tyler Tran, Nathaniel Gyory, Anthony M. Harrison, Wallace E. Lawson, Ravenna Thielstrom, Hunter Thompson, Taaren Singh, J. Gregory Trafton
Abstract: Vision language models (VLMs) are designed to extract relevant visuospatial information from images. Some research suggests that VLMs can exhibit humanlike scene understanding, while other investigations reveal difficulties in their ability to process relational information. To achieve widespread applicability, VLMs must perform reliably, yielding comparable competence across a wide variety of related tasks. We sought to test how reliable these architectures are at engaging in trivial spatial cognition, e.g., recognizing whether one object is left of another in an uncluttered scene. We developed a benchmark dataset -- TableTest -- whose images depict 3D scenes of objects arranged on a table, and used it to evaluate state-of-the-art VLMs. Results show that performance could be degraded by minor variations of prompts that use logically equivalent descriptions. These analyses suggest limitations in how VLMs may reason about spatial relations in real-world applications. They also reveal novel opportunities for bolstering image caption corpora for more efficient training and testing.
Authors: Theodoros Kouzelis, Efstathios Karypidis, Ioannis Kakogeorgiou, Spyros Gidaris, Nikos Komodakis
Abstract: Latent diffusion models (LDMs) dominate high-quality image generation, yet integrating representation learning with generative modeling remains a challenge. We introduce a novel generative image modeling framework that seamlessly bridges this gap by leveraging a diffusion model to jointly model low-level image latents (from a variational autoencoder) and high-level semantic features (from a pretrained self-supervised encoder like DINO). Our latent-semantic diffusion approach learns to generate coherent image-feature pairs from pure noise, significantly enhancing both generative quality and training efficiency, all while requiring only minimal modifications to standard Diffusion Transformer architectures. By eliminating the need for complex distillation objectives, our unified design simplifies training and unlocks a powerful new inference strategy: Representation Guidance, which leverages learned semantics to steer and refine image generation. Evaluated in both conditional and unconditional settings, our method delivers substantial improvements in image quality and training convergence speed, establishing a new direction for representation-aware generative modeling.
Authors: Long Lian, Yifan Ding, Yunhao Ge, Sifei Liu, Hanzi Mao, Boyi Li, Marco Pavone, Ming-Yu Liu, Trevor Darrell, Adam Yala, Yin Cui
Abstract: Generating detailed and accurate descriptions for specific regions in images and videos remains a fundamental challenge for vision-language models. We introduce the Describe Anything Model (DAM), a model designed for detailed localized captioning (DLC). DAM preserves both local details and global context through two key innovations: a focal prompt, which ensures high-resolution encoding of targeted regions, and a localized vision backbone, which integrates precise localization with its broader context. To tackle the scarcity of high-quality DLC data, we propose a Semi-supervised learning (SSL)-based Data Pipeline (DLC-SDP). DLC-SDP starts with existing segmentation datasets and expands to unlabeled web images using SSL. We introduce DLC-Bench, a benchmark designed to evaluate DLC without relying on reference captions. DAM sets new state-of-the-art on 7 benchmarks spanning keyword-level, phrase-level, and detailed multi-sentence localized image and video captioning.
Authors: Le Zhuo, Liangbing Zhao, Sayak Paul, Yue Liao, Renrui Zhang, Yi Xin, Peng Gao, Mohamed Elhoseiny, Hongsheng Li
Abstract: Recent text-to-image diffusion models achieve impressive visual quality through extensive scaling of training data and model parameters, yet they often struggle with complex scenes and fine-grained details. Inspired by the self-reflection capabilities emergent in large language models, we propose ReflectionFlow, an inference-time framework enabling diffusion models to iteratively reflect upon and refine their outputs. ReflectionFlow introduces three complementary inference-time scaling axes: (1) noise-level scaling to optimize latent initialization; (2) prompt-level scaling for precise semantic guidance; and most notably, (3) reflection-level scaling, which explicitly provides actionable reflections to iteratively assess and correct previous generations. To facilitate reflection-level scaling, we construct GenRef, a large-scale dataset comprising 1 million triplets, each containing a reflection, a flawed image, and an enhanced image. Leveraging this dataset, we efficiently perform reflection tuning on state-of-the-art diffusion transformer, FLUX.1-dev, by jointly modeling multimodal inputs within a unified framework. Experimental results show that ReflectionFlow significantly outperforms naive noise-level scaling methods, offering a scalable and compute-efficient solution toward higher-quality image synthesis on challenging tasks.
Authors: Yimu Wang, Xuye Liu, Wei Pang, Li Ma, Shuai Yuan, Paul Debevec, Ning Yu
Abstract: Recent advances in diffusion models have revolutionized video generation, offering superior temporal consistency and visual quality compared to traditional generative adversarial networks-based approaches. While this emerging field shows tremendous promise in applications, it faces significant challenges in motion consistency, computational efficiency, and ethical considerations. This survey provides a comprehensive review of diffusion-based video generation, examining its evolution, technical foundations, and practical applications. We present a systematic taxonomy of current methodologies, analyze architectural innovations and optimization strategies, and investigate applications across low-level vision tasks such as denoising and super-resolution. Additionally, we explore the synergies between diffusionbased video generation and related domains, including video representation learning, question answering, and retrieval. Compared to the existing surveys (Lei et al., 2024a;b; Melnik et al., 2024; Cao et al., 2023; Xing et al., 2024c) which focus on specific aspects of video generation, such as human video synthesis (Lei et al., 2024a) or long-form content generation (Lei et al., 2024b), our work provides a broader, more updated, and more fine-grained perspective on diffusion-based approaches with a special section for evaluation metrics, industry solutions, and training engineering techniques in video generation. This survey serves as a foundational resource for researchers and practitioners working at the intersection of diffusion models and video generation, providing insights into both the theoretical frameworks and practical implementations that drive this rapidly evolving field. A structured list of related works involved in this survey is also available on https://github.com/Eyeline-Research/Survey-Video-Diffusion.
URLs: https://github.com/Eyeline-Research/Survey-Video-Diffusion.
Authors: Ziqi Pang, Yu-Xiong Wang
Abstract: We propose MR. Video, an agentic long video understanding framework that demonstrates the simple yet effective MapReduce principle for processing long videos: (1) Map: independently and densely perceiving short video clips, and (2) Reduce: jointly aggregating information from all clips. Compared with sequence-to-sequence vision-language models (VLMs), MR. Video performs detailed short video perception without being limited by context length. Compared with existing video agents that typically rely on sequential key segment selection, the Map operation enables simpler and more scalable sequence parallel perception of short video segments. Its Reduce step allows for more comprehensive context aggregation and reasoning, surpassing explicit key segment retrieval. This MapReduce principle is applicable to both VLMs and video agents, and we use LLM agents to validate its effectiveness. In practice, MR. Video employs two MapReduce stages: (A) Captioning: generating captions for short video clips (map), then standardizing repeated characters and objects into shared names (reduce); (B) Analysis: for each user question, analyzing relevant information from individual short videos (map), and integrating them into a final answer (reduce). MR. Video achieves over 10% accuracy improvement on the challenging LVBench compared to state-of-the-art VLMs and video agents. Code is available at: https://github.com/ziqipang/MR-Video
Authors: Yucheng Li, Huiqiang Jiang, Chengruidong Zhang, Qianhui Wu, Xufang Luo, Surin Ahn, Amir H. Abdi, Dongsheng Li, Jianfeng Gao, Yuqing Yang, Lili Qiu
Abstract: The integration of long-context capabilities with visual understanding unlocks unprecedented potential for Vision Language Models (VLMs). However, the quadratic attention complexity during the pre-filling phase remains a significant obstacle to real-world deployment. To overcome this limitation, we introduce MMInference (Multimodality Million tokens Inference), a dynamic sparse attention method that accelerates the prefilling stage for long-context multi-modal inputs. First, our analysis reveals that the temporal and spatial locality of video input leads to a unique sparse pattern, the Grid pattern. Simultaneously, VLMs exhibit markedly different sparse distributions across different modalities. We introduce a permutation-based method to leverage the unique Grid pattern and handle modality boundary issues. By offline search the optimal sparse patterns for each head, MMInference constructs the sparse distribution dynamically based on the input. We also provide optimized GPU kernels for efficient sparse computations. Notably, MMInference integrates seamlessly into existing VLM pipelines without any model modifications or fine-tuning. Experiments on multi-modal benchmarks-including Video QA, Captioning, VisionNIAH, and Mixed-Modality NIAH-with state-of-the-art long-context VLMs (LongVila, LlavaVideo, VideoChat-Flash, Qwen2.5-VL) show that MMInference accelerates the pre-filling stage by up to 8.3x at 1M tokens while maintaining accuracy. Our code is available at https://aka.ms/MMInference.
Authors: Kenan Tang, Yanhong Li, Yao Qin
Abstract: Recent prompt-based image editing models have demonstrated impressive prompt-following capability at structural editing tasks. However, existing models still fail to perform local edits, follow detailed editing prompts, or maintain global image quality beyond a single editing step. To address these challenges, we introduce SPICE, a training-free workflow that accepts arbitrary resolutions and aspect ratios, accurately follows user requirements, and improves image quality consistently during more than 100 editing steps. By synergizing the strengths of a base diffusion model and a Canny edge ControlNet model, SPICE robustly handles free-form editing instructions from the user. SPICE outperforms state-of-the-art baselines on a challenging realistic image-editing dataset consisting of semantic editing (object addition, removal, replacement, and background change), stylistic editing (texture changes), and structural editing (action change) tasks. Not only does SPICE achieve the highest quantitative performance according to standard evaluation metrics, but it is also consistently preferred by users over existing image-editing methods. We release the workflow implementation for popular diffusion model Web UIs to support further research and artistic exploration.
Authors: Abhishek Tyagi, Charu Gaur
Abstract: We present an autonomous aerial surveillance platform, Veg, designed as a fault-tolerant quadcopter system that integrates visual SLAM for GPS-independent navigation, advanced control architecture for dynamic stability, and embedded vision modules for real-time object and face recognition. The platform features a cascaded control design with an LQR inner-loop and PD outer-loop trajectory control. It leverages ORB-SLAM3 for 6-DoF localization and loop closure, and supports waypoint-based navigation through Dijkstra path planning over SLAM-derived maps. A real-time Failure Detection and Identification (FDI) system detects rotor faults and executes emergency landing through re-routing. The embedded vision system, based on a lightweight CNN and PCA, enables onboard object detection and face recognition with high precision. The drone operates fully onboard using a Raspberry Pi 4 and Arduino Nano, validated through simulations and real-world testing. This work consolidates real-time localization, fault recovery, and embedded AI on a single platform suitable for constrained environments.
Authors: Meher Boulaabi, Takwa Ben A\"icha Gader, Afef Kacem Echi, Zied Bouraoui
Abstract: Diabetic retinopathy (DR) is a leading cause of blindness worldwide, underscoring the importance of early detection for effective treatment. However, automated DR classification remains challenging due to variations in image quality, class imbalance, and pixel-level similarities that hinder model training. To address these issues, we propose a robust preprocessing pipeline incorporating image cropping, Contrast-Limited Adaptive Histogram Equalization (CLAHE), and targeted data augmentation to improve model generalization and resilience. Our approach leverages the Swin Transformer, which utilizes hierarchical token processing and shifted window attention to efficiently capture fine-grained features while maintaining linear computational complexity. We validate our method on the Aptos and IDRiD datasets for multi-class DR classification, achieving accuracy rates of 89.65% and 97.40%, respectively. These results demonstrate the effectiveness of our model, particularly in detecting early-stage DR, highlighting its potential for improving automated retinal screening in clinical settings.
Authors: Donggyun Kim, Chanwoo Kim, Seunghoon Hong
Abstract: While test-time fine-tuning is beneficial in few-shot learning, the need for multiple backpropagation steps can be prohibitively expensive in real-time or low-resource scenarios. To address this limitation, we propose an approach that emulates gradient descent without computing gradients, enabling efficient test-time adaptation. Specifically, we formulate gradient descent as an Euler discretization of an ordinary differential equation (ODE) and train an auxiliary network to predict the task-conditional drift using only the few-shot support set. The adaptation then reduces to a simple numerical integration (e.g., via the Euler method), which requires only a few forward passes of the auxiliary network -- no gradients or forward passes of the target model are needed. In experiments on cross-domain few-shot classification using the Meta-Dataset and CDFSL benchmarks, our method significantly improves out-of-domain performance over the non-fine-tuned baseline while incurring only 6\% of the memory cost and 0.02\% of the computation time of standard fine-tuning, thus establishing a practical middle ground between direct transfer and fully fine-tuned approaches.
Authors: Yike Zhang, Eduardo Davalos, Jack Noble
Abstract: Accurate 6D pose estimation has gained more attention over the years for robotics-assisted tasks that require precise interaction with physical objects. This paper presents an interactive 3D-to-2D visualization and annotation tool to support the 6D pose estimation research community. To the best of our knowledge, the proposed work is the first tool that allows users to visualize and manipulate 3D objects interactively on a 2D real-world scene, along with a comprehensive user study. This system supports robust 6D camera pose annotation by providing both visual cues and spatial relationships to determine object position and orientation in various environments. The annotation feature in Vision6D is particularly helpful in scenarios where the transformation matrix between the camera and world objects is unknown, as it enables accurate annotation of these objects' poses using only the camera intrinsic matrix. This capability serves as a foundational step in developing and training advanced pose estimation models across various domains. We evaluate Vision6D's effectiveness by utilizing widely-used open-source pose estimation datasets Linemod and HANDAL through comparisons between the default ground-truth camera poses with manual annotations. A user study was performed to show that Vision6D generates accurate pose annotations via visual cues in an intuitive 3D user interface. This approach aims to bridge the gap between 2D scene projections and 3D scenes, offering an effective way for researchers and developers to solve 6D pose annotation related problems. The software is open-source and publicly available at https://github.com/InteractiveGL/vision6D.
Authors: Sarath Shekkizhar, Romain Cosentino
Abstract: This paper investigates multimodal agents, in particular, OpenAI's Computer-User Agent (CUA), trained to control and complete tasks through a standard computer interface, similar to humans. We evaluated the agent's performance on the New York Times Wordle game to elicit model behaviors and identify shortcomings. Our findings revealed a significant discrepancy in the model's ability to recognize colors correctly depending on the context. The model had a $5.36\%$ success rate over several hundred runs across a week of Wordle. Despite the immense enthusiasm surrounding AI agents and their potential to usher in Artificial General Intelligence (AGI), our findings reinforce the fact that even simple tasks present substantial challenges for today's frontier AI models. We conclude with a discussion of the potential underlying causes, implications for future development, and research directions to improve these AI systems.
Authors: Jeremy Goldwasser, Giles Hooker
Abstract: Counterfactuals are a popular framework for interpreting machine learning predictions. These what if explanations are notoriously challenging to create for computer vision models: standard gradient-based methods are prone to produce adversarial examples, in which imperceptible modifications to image pixels provoke large changes in predictions. We introduce a new, easy-to-implement framework for counterfactual images that can flexibly adapt to contemporary advances in generative modeling. Our method, Counterfactual Attacks, resembles an adversarial attack on the representation of the image along a low-dimensional manifold. In addition, given an auxiliary dataset of image descriptors, we show how to accompany counterfactuals with feature attribution that quantify the changes between the original and counterfactual images. These importance scores can be aggregated into global counterfactual explanations that highlight the overall features driving model predictions. While this unification is possible for any counterfactual method, it has particular computational efficiency for ours. We demonstrate the efficacy of our approach with the MNIST and CelebA datasets.
Authors: Michel Berthier, Nicoletta Prencipe, Edoardo Provenzi
Abstract: We propose a perceptual chromatic adaptation transform for white balance that makes use of split-quaternions. The novelty of the present work, which is motivated by a recently developed quantum-like model of color perception, consists at stressing the link between the algebraic structures appearing in this model and a certain sub-algebra of the split-quaternions. We show the potentiality of this approach for color image processing applications by proposing a chromatic adaptation transform, implemented via an appropriate use of the split-quaternion multiplication. Moreover, quantitative comparisons with the widely used state-of-the art von Kries chromatic adaptation transform are provided.
Authors: Eammon A. Littler, Emmanuel A. Mannoh, Ethan P. M. LaRochelle
Abstract: Standardized performance evaluation of fluorescence imaging systems remains a critical unmet need in the field of fluorescence-guided surgery (FGS). While the American Association of Physicists in Medicine (AAPM) TG311 report and recent FDA draft guidance provide recommended metrics for system characterization, practical tools for extracting these metrics remain limited, inconsistent, and often inaccessible. We present QUEL-QAL, an open-source Python library designed to streamline and standardize the quantitative analysis of fluorescence images using solid reference targets. The library provides a modular, reproducible workflow that includes region of interest (ROI) detection, statistical analysis, and visualization capabilities. QUEL-QAL supports key metrics such as response linearity, limit of detection, depth sensitivity, and spatial resolution, in alignment with regulatory and academic guidance. Built on widely adopted Python packages, the library is designed to be extensible, enabling users to adapt it to novel target designs and analysis protocols. By promoting transparency, reproducibility, and regulatory alignment, QUEL-QAL offers a foundational tool to support standardized benchmarking and accelerate the development and evaluation of fluorescence imaging systems.
Authors: Zizhi Chen, Xinyu Zhang, Minghao Han, Yizhou Liu, Ziyun Qian, Weifeng Zhang, Xukun Zhang, Jingwei Wei, Lihua Zhang
Abstract: In histopathology, tissue sections are typically stained using common H&E staining or special stains (MAS, PAS, PASM, etc.) to clearly visualize specific tissue structures. The rapid advancement of deep learning offers an effective solution for generating virtually stained images, significantly reducing the time and labor costs associated with traditional histochemical staining. However, a new challenge arises in separating the fundamental visual characteristics of tissue sections from the visual differences induced by staining agents. Additionally, virtual staining often overlooks essential pathological knowledge and the physical properties of staining, resulting in only style-level transfer. To address these issues, we introduce, for the first time in virtual staining tasks, a pathological vision-language large model (VLM) as an auxiliary tool. We integrate contrastive learnable prompts, foundational concept anchors for tissue sections, and staining-specific concept anchors to leverage the extensive knowledge of the pathological VLM. This approach is designed to describe, frame, and enhance the direction of virtual staining. Furthermore, we have developed a data augmentation method based on the constraints of the VLM. This method utilizes the VLM's powerful image interpretation capabilities to further integrate image style and structural information, proving beneficial in high-precision pathological diagnostics. Extensive evaluations on publicly available multi-domain unpaired staining datasets demonstrate that our method can generate highly realistic images and enhance the accuracy of downstream tasks, such as glomerular detection and segmentation. Our code is available at: https://github.com/CZZZZZZZZZZZZZZZZZ/VPGAN-HARBOR
Authors: Dip Roy
Abstract: In medical imaging, anomaly detection is a vital element of healthcare diagnostics, especially for neurological conditions which can be life-threatening. Conventional deterministic methods often fall short when it comes to capturing the inherent uncertainty of anomaly detection tasks. This paper introduces a Bayesian Variational Autoencoder (VAE) equipped with multi-head attention mechanisms for detecting anomalies in brain magnetic resonance imaging (MRI). For the purpose of improving anomaly detection performance, we incorporate both epistemic and aleatoric uncertainty estimation through Bayesian inference. The model was tested on the BraTS2020 dataset, and the findings were a 0.83 ROC AUC and a 0.83 PR AUC. The data in our paper suggests that modeling uncertainty is an essential component of anomaly detection, enhancing both performance and interpretability and providing confidence estimates, as well as anomaly predictions, for clinicians to leverage in making medical decisions.
Authors: Tatsuhito Hasegawa, Shunsuke Sakai
Abstract: In deep learning-based classification tasks, the softmax function's temperature parameter $T$ critically influences the output distribution and overall performance. This study presents a novel theoretical insight that the optimal temperature $T^*$ is uniquely determined by the dimensionality of the feature representations, thereby enabling training-free determination of $T^*$. Despite this theoretical grounding, empirical evidence reveals that $T^*$ fluctuates under practical conditions owing to variations in models, datasets, and other confounding factors. To address these influences, we propose and optimize a set of temperature determination coefficients that specify how $T^*$ should be adjusted based on the theoretical relationship to feature dimensionality. Additionally, we insert a batch normalization layer immediately before the output layer, effectively stabilizing the feature space. Building on these coefficients and a suite of large-scale experiments, we develop an empirical formula to estimate $T^*$ without additional training while also introducing a corrective scheme to refine $T^*$ based on the number of classes and task complexity. Our findings confirm that the derived temperature not only aligns with the proposed theoretical perspective but also generalizes effectively across diverse tasks, consistently enhancing classification performance and offering a practical, training-free solution for determining $T^*$.
Authors: Kai Chen, Xiaodong Zhao, Yujie Huang, Guoyu Fang, Xiao Song, Ruiping Wang, Ziyuan Wang
Abstract: The analysis and prediction of agent trajectories are crucial for decision-making processes in intelligent systems, with precise short-term trajectory forecasting being highly significant across a range of applications. Agents and their social interactions have been quantified and modeled by researchers from various perspectives; however, substantial limitations exist in the current work due to the inherent high uncertainty of agent intentions and the complex higher-order influences among neighboring groups. SocialMOIF is proposed to tackle these challenges, concentrating on the higher-order intention interactions among neighboring groups while reinforcing the primary role of first-order intention interactions between neighbors and the target agent. This method develops a multi-order intention fusion model to achieve a more comprehensive understanding of both direct and indirect intention information. Within SocialMOIF, a trajectory distribution approximator is designed to guide the trajectories toward values that align more closely with the actual data, thereby enhancing model interpretability. Furthermore, a global trajectory optimizer is introduced to enable more accurate and efficient parallel predictions. By incorporating a novel loss function that accounts for distance and direction during training, experimental results demonstrate that the model outperforms previous state-of-the-art baselines across multiple metrics in both dynamic and static datasets.
Authors: Biao Wu, Diankai Zhang, Shaoli Liu, Si Gao, Chengjian Zheng, Ning Wang
Abstract: As a fundamental challenge in visual computing, video super-resolution (VSR) focuses on reconstructing highdefinition video sequences from their degraded lowresolution counterparts. While deep convolutional neural networks have demonstrated state-of-the-art performance in spatial-temporal super-resolution tasks, their computationally intensive nature poses significant deployment challenges for resource-constrained edge devices, particularly in real-time mobile video processing scenarios where power efficiency and latency constraints coexist. In this work, we propose a Reparameterizable Architecture for High Fidelity Video Super Resolution method, named RepNet-VSR, for real-time 4x video super-resolution. On the REDS validation set, the proposed model achieves 27.79 dB PSNR when processing 180p to 720p frames in 103 ms per 10 frames on a MediaTek Dimensity NPU. The competition results demonstrate an excellent balance between restoration quality and deployment efficiency. The proposed method scores higher than the previous champion algorithm of MAI video super-resolution challenge.
Authors: Md Abdul Baset Sarker, Art Nguyen, Sigmond Kukla, Kevin Fite, Masudul H. Imtiaz
Abstract: This paper introduces a novel AI vision-enabled pediatric prosthetic hand designed to assist children aged 10-12 with upper limb disabilities. The prosthesis features an anthropomorphic appearance, multi-articulating functionality, and a lightweight design that mimics a natural hand, making it both accessible and affordable for low-income families. Using 3D printing technology and integrating advanced machine vision, sensing, and embedded computing, the prosthetic hand offers a low-cost, customizable solution that addresses the limitations of current myoelectric prostheses. A micro camera is interfaced with a low-power FPGA for real-time object detection and assists with precise grasping. The onboard DL-based object detection and grasp classification models achieved accuracies of 96% and 100% respectively. In the force prediction, the mean absolute error was found to be 0.018. The features of the proposed prosthetic hand can thus be summarized as: a) a wrist-mounted micro camera for artificial sensing, enabling a wide range of hand-based tasks; b) real-time object detection and distance estimation for precise grasping; and c) ultra-low-power operation that delivers high performance within constrained power and resource limits.
Authors: Phuong Quynh Le, J\"org Schl\"otterer, Christin Seifert
Abstract: Machine learning models tend to learn spurious features - features that strongly correlate with target labels but are not causal. Existing approaches to mitigate models' dependence on spurious features work in some cases, but fail in others. In this paper, we systematically analyze how and where neural networks encode spurious correlations. We introduce the neuron spurious score, an XAI-based diagnostic measure to quantify a neuron's dependence on spurious features. We analyze both convolutional neural networks (CNNs) and vision transformers (ViTs) using architecture-specific methods. Our results show that spurious features are partially disentangled, but the degree of disentanglement varies across model architectures. Furthermore, we find that the assumptions behind existing mitigation methods are incomplete. Our results lay the groundwork for the development of novel methods to mitigate spurious correlations and make AI models safer to use in practice.
Authors: Jingchen Zou, Jianqiang Li, Gabriel Jimenez, Qing Zhao, Daniel Racoceanu, Matias Cosarinsky, Enzo Ferrante, Guanghui Fu
Abstract: The performance of medical image segmentation models is usually evaluated using metrics like the Dice score and Hausdorff distance, which compare predicted masks to ground truth annotations. However, when applying the model to unseen data, such as in clinical settings, it is often impractical to annotate all the data, making the model's performance uncertain. To address this challenge, we propose the Segmentation Performance Evaluator (SPE), a framework for estimating segmentation models' performance on unlabeled data. This framework is adaptable to various evaluation metrics and model architectures. Experiments on six publicly available datasets across six evaluation metrics including pixel-based metrics such as Dice score and distance-based metrics like HD95, demonstrated the versatility and effectiveness of our approach, achieving a high correlation (0.956$\pm$0.046) and low MAE (0.025$\pm$0.019) compare with real Dice score on the independent test set. These results highlight its ability to reliably estimate model performance without requiring annotations. The SPE framework integrates seamlessly into any model training process without adding training overhead, enabling performance estimation and facilitating the real-world application of medical image segmentation algorithms. The source code is publicly available
Authors: Blerim Abdullai, Tony Wang, Xinyuan Qiao, Florian Shkurti, Timothy D. Barfoot
Abstract: GNSS is unreliable, inaccurate, and insufficient in many real-time autonomous field applications. In this work, we present a GNSS-free global localization solution that contains a method of registering imaging radar on the ground with overhead RGB imagery, with joint optimization of relative poses from odometry and global poses from our overhead registration. Previous works have used various combinations of ground sensors and overhead imagery, and different feature extraction and matching methods. These include various handcrafted and deep-learning-based methods for extracting features from overhead imagery. Our work presents insights on extracting essential features from RGB overhead images for effective global localization against overhead imagery using only ground radar and a single georeferenced initial guess. We motivate our method by evaluating it on datasets in diverse geographic conditions and robotic platforms, including on an Unmanned Surface Vessel (USV) as well as urban and suburban driving datasets.
Authors: Chance J. Hamilton, Alfredo Weitzenfeld
Abstract: This paper presents the Visual Place Cell Encoding (VPCE) model, a biologically inspired computational framework for simulating place cell-like activation using visual input. Drawing on evidence that visual landmarks play a central role in spatial encoding, the proposed VPCE model activates visual place cells by clustering high-dimensional appearance features extracted from images captured by a robot-mounted camera. Each cluster center defines a receptive field, and activation is computed based on visual similarity using a radial basis function. We evaluate whether the resulting activation patterns correlate with key properties of biological place cells, including spatial proximity, orientation alignment, and boundary differentiation. Experiments demonstrate that the VPCE can distinguish between visually similar yet spatially distinct locations and adapt to environment changes such as the insertion or removal of walls. These results suggest that structured visual input, even in the absence of motion cues or reward-driven learning, is sufficient to generate place-cell-like spatial representations and support biologically inspired cognitive mapping.
Authors: Baichuan Zeng
Abstract: Extended Reality (XR), encompassing Augmented Reality (AR), Virtual Reality (VR) and Mixed Reality (MR), is a transformative technology bridging the physical and virtual world and it has diverse potential which will be ubiquitous in the future. This review examines XR's evolution through foundational framework - hardware ranging from monitors to sensors and software ranging from visual tasks to user interface; highlights state of the art (SOTA) XR products with the comparison and analysis of performance based on their foundational framework; discusses how commercial XR devices can support the demand of high-quality performance focusing on spatial intelligence. For future directions, attention should be given to the integration of multi-modal AI and IoT-driven digital twins to enable adaptive XR systems. With the concept of spatial intelligence, future XR should establish a new digital space with realistic experience that benefits humanity. This review underscores the pivotal role of AI in unlocking XR as the next frontier in human-computer interaction.
Authors: Peter Fletcher
Abstract: I introduce a formalism for representing the syntax of recursively structured graph-like patterns. It does not use production rules, like a conventional graph grammar, but represents the syntactic structure in a more direct and declarative way. The grammar and the pattern are both represented as networks, and parsing is seen as the construction of a homomorphism from the pattern to the grammar. The grammars can represent iterative, hierarchical and nested recursive structure in more than one dimension. This supports a highly parallel style of parsing, in which all aspects of pattern recognition (feature detection, segmentation, parsing, filling in missing symbols, top-down and bottom-up inference) are integrated into a single process, to exploit the synergy between them. The emphasis of this paper is on underlying theoretical issues, but I also give some example runs to illustrate the error-tolerant parsing of complex recursively structured patterns of 50-1000 symbols, involving variability in geometric relationships, blurry and indistinct symbols, overlapping symbols, cluttered images, and erased patches.
Authors: Hardik Shah, Jiaxu Xing, Nico Messikommer, Boyang Sun, Marc Pollefeys, Davide Scaramuzza
Abstract: Understanding how humans leverage prior knowledge to navigate unseen environments while making exploratory decisions is essential for developing autonomous robots with similar abilities. In this work, we propose ForesightNav, a novel exploration strategy inspired by human imagination and reasoning. Our approach equips robotic agents with the capability to predict contextual information, such as occupancy and semantic details, for unexplored regions. These predictions enable the robot to efficiently select meaningful long-term navigation goals, significantly enhancing exploration in unseen environments. We validate our imagination-based approach using the Structured3D dataset, demonstrating accurate occupancy prediction and superior performance in anticipating unseen scene geometry. Our experiments show that the imagination module improves exploration efficiency in unseen environments, achieving a 100% completion rate for PointNav and an SPL of 67% for ObjectNav on the Structured3D Validation split. These contributions demonstrate the power of imagination-driven reasoning for autonomous systems to enhance generalizable and efficient exploration.
Authors: Jiani Huang, Ziyang Li, Mayur Naik, Ser-Nam Lim
Abstract: Supervised approaches for learning spatio-temporal scene graphs (STSG) from video are greatly hindered due to their reliance on STSG-annotated videos, which are labor-intensive to construct at scale. Is it feasible to instead use readily available video captions as weak supervision? To address this question, we propose LASER, a neuro-symbolic framework to enable training STSG generators using only video captions. LASER employs large language models to first extract logical specifications with rich spatio-temporal semantic information from video captions. LASER then trains the underlying STSG generator to align the predicted STSG with the specification. The alignment algorithm overcomes the challenges of weak supervision by leveraging a differentiable symbolic reasoner and using a combination of contrastive, temporal, and semantics losses. The overall approach efficiently trains low-level perception models to extract a fine-grained STSG that conforms to the video caption. In doing so, it enables a novel methodology for learning STSGs without tedious annotations. We evaluate our method on three video datasets: OpenPVSG, 20BN, and MUGEN. Our approach demonstrates substantial improvements over fully-supervised baselines, achieving a unary predicate prediction accuracy of 27.78% (+12.65%) and a binary recall@5 of 0.42 (+0.22) on OpenPVSG. Additionally, LASER exceeds baselines by 7% on 20BN and 5.2% on MUGEN in terms of overall predicate prediction accuracy.
Authors: Asad Aali, Giannis Daras, Brett Levac, Sidharth Kumar, Alexandros G. Dimakis, Jonathan I. Tamir
Abstract: We provide a framework for solving inverse problems with diffusion models learned from linearly corrupted data. Firstly, we extend the Ambient Diffusion framework to enable training directly from measurements corrupted in the Fourier domain. Subsequently, we train diffusion models for MRI with access only to Fourier subsampled multi-coil measurements at acceleration factors R= 2,4,6,8. Secondly, we propose Ambient Diffusion Posterior Sampling (A-DPS), a reconstruction algorithm that leverages generative models pre-trained on one type of corruption (e.g. image inpainting) to perform posterior sampling on measurements from a different forward process (e.g. image blurring). For MRI reconstruction in high acceleration regimes, we observe that A-DPS models trained on subsampled data are better suited to solving inverse problems than models trained on fully sampled data. We also test the efficacy of A-DPS on natural image datasets (CelebA, FFHQ, and AFHQ) and show that A-DPS can sometimes outperform models trained on clean data for several image restoration tasks in both speed and performance.
Authors: Yui Lo, Yuqian Chen, Dongnan Liu, Wan Liu, Leo Zekelman, Fan Zhang, Yogesh Rathi, Nikos Makris, Alexandra J. Golby, Weidong Cai, Lauren J. O'Donnell
Abstract: Shape plays an important role in computer graphics, offering informative features to convey an object's morphology and functionality. Shape analysis in brain imaging can help interpret structural and functionality correlations of the human brain. In this work, we investigate the shape of the brain's 3D white matter connections and its potential predictive relationship to human cognitive function. We reconstruct brain connections as sequences of 3D points using diffusion magnetic resonance imaging (dMRI) tractography. To describe each connection, we extract 12 shape descriptors in addition to traditional dMRI connectivity and tissue microstructure features. We introduce a novel framework, Shape--fused Fiber Cluster Transformer (SFFormer), that leverages a multi-head cross-attention feature fusion module to predict subject-specific language performance based on dMRI tractography. We assess the performance of the method on a large dataset including 1065 healthy young adults. The results demonstrate that both the transformer-based SFFormer model and its inter/intra feature fusion with shape, microstructure, and connectivity are informative, and together, they improve the prediction of subject-specific language performance scores. Overall, our results indicate that the shape of the brain's connections is predictive of human language function.
Authors: Jingqun Tang, Chunhui Lin, Zhen Zhao, Shu Wei, Binghong Wu, Qi Liu, Hao Feng, Yang Li, Siqi Wang, Lei Liao, Wei Shi, Yuliang Liu, Hao Liu, Yuan Xie, Xiang Bai, Can Huang
Abstract: Text-centric visual question answering (VQA) has made great strides with the development of Multimodal Large Language Models (MLLMs), yet open-source models still fall short of leading models like GPT4V and Gemini, partly due to a lack of extensive, high-quality instruction tuning data. To this end, we introduce a new approach for creating a massive, high-quality instruction-tuning dataset, Square-10M, which is generated using closed-source MLLMs. The data construction process, termed Square, consists of four steps: Self-Questioning, Answering, Reasoning, and Evaluation. Our experiments with Square-10M led to three key findings: 1) Our model, TextSquare, considerably surpasses open-source previous state-of-the-art Text-centric MLLMs and sets a new standard on OCRBench(62.2%). It even outperforms top-tier models like GPT4V and Gemini in 6 of 10 text-centric benchmarks. 2) Additionally, we demonstrate the critical role of VQA reasoning data in offering comprehensive contextual insights for specific questions. This not only improves accuracy but also significantly mitigates hallucinations. Specifically, TextSquare scores an average of 75.1% across four general VQA and hallucination evaluation datasets, outperforming previous state-of-the-art models. 3) Notably, the phenomenon observed in scaling text-centric VQA datasets reveals a vivid pattern: the exponential increase of instruction tuning data volume is directly proportional to the improvement in model performance, thereby validating the necessity of the dataset scale and the high quality of Square-10M.
Authors: Aarya Patel, Hamid Laga, Ojaswa Sharma
Abstract: Neural implicit representations have emerged as a powerful paradigm for 3D reconstruction. However, despite their success, existing methods fail to capture fine geometric details and thin structures, especially in scenarios where only sparse multi-view RGB images of the objects of interest are available. This paper shows that training neural representations with first-order differential properties (surface normals) leads to highly accurate 3D surface reconstruction, even with as few as two RGB images. Using input RGB images, we compute approximate ground-truth surface normals from depth maps produced by an off-the-shelf monocular depth estimator. During training, we directly locate the surface point of the SDF network and supervise its normal with the one estimated from the depth map. Extensive experiments demonstrate that our method achieves state-of-the-art reconstruction accuracy with a minimal number of views, capturing intricate geometric details and thin structures that were previously challenging to capture.
Authors: Pit Henrich, Franziska Mathis-Ullrich
Abstract: We introduce a novel approach for the precise localization of 67 anatomical structures from single depth images captured from the exterior of the human body. Our method uses a multi-class occupancy network, trained using segmented CT scans augmented with body-pose changes, and incorporates a specialized sampling strategy to handle densely packed internal organs. Our contributions include the application of occupancy networks for occluded structure localization, a robust method for estimating anatomical positions from depth images, and the creation of detailed, individualized 3D anatomical atlases. We outperform localization using template matching and provide qualitative real-world reconstructions. This method promises improvements in automated medical imaging and diagnostic procedures by offering accurate, non-invasive localization of critical anatomical structures.
Authors: Jinmiao Zhao, Zelin Shi, Chuang Yu, Yunpeng Liu, Yimian Dai
Abstract: Recently, single-frame infrared small target (SIRST) detection technology has attracted wide-spread attention. However, due to the intrinsic feature scarcity in infrared small targets, precise segmentation of small targets from complex backgrounds remains a significant challenge. Different from most existing deep learning-based methods that focus on improving network architectures, we propose a feature-enhanced and sensitivity-tunable (FEST) framework, which is compatible with existing SIRST detection networks and further enhances their detection performance. The FEST framework improves the model's robustness from two aspects: feature enhancement and target confidence regulation. For feature enhancement, on the one hand, we adopt a multi-scale fusion strategy, which can effectively improve the model's perception and adaptability to multi-scale features of multi-size targets. On the other hand, we construct an edge enhancement difficulty mining (EEDM) loss based on the analysis of the task characteristics, which helps guide the network to continuously focus on challenging target regions and edge features during training. For target confidence regulation, we design an adjustable sensitivity (AS) strategy for network post-processing. This strategy not only enhances the adaptability of the network in complex scenarios, but also significantly improves the detection rate of infrared small targets while maintaining segmentation accuracy. Extensive experimental results show that our FEST framework can significantly enhance the performance of existing SIRST detection networks. Notably, the multi-scale direction-aware network (MSDA-Net) equipped with the FEST framework won the first prize in the PRCV 2024 wide-area infrared small target detection competition.
Authors: Kai Li, Yupeng Deng, Jingbo Chen, Yu Meng, Zhihao Xi, Junxian Ma, Chenhao Wang, Maolin Wang, Xiangyu Zhao
Abstract: Extracting polygonal building footprints from off-nadir imagery is crucial for diverse applications. Current deep-learning-based extraction approaches predominantly rely on semantic segmentation paradigms and post-processing algorithms, limiting their boundary precision and applicability. However, existing polygonal extraction methodologies are inherently designed for near-nadir imagery and fail under the geometric complexities introduced by off-nadir viewing angles. To address these challenges, this paper introduces Polygonal Footprint Network (PolyFootNet), a novel deep-learning framework that directly outputs polygonal building footprints without requiring external post-processing steps. PolyFootNet employs a High-Quality Mask Prompter to generate precise roof masks, which guide polygonal vertex extraction in a unified model pipeline. A key contribution of PolyFootNet is introducing the Self Offset Attention mechanism, grounded in Nadaraya-Watson regression, to effectively mitigate the accuracy discrepancy observed between low-rise and high-rise buildings. This approach allows low-rise building predictions to leverage angular corrections learned from high-rise building offsets, significantly enhancing overall extraction accuracy. Additionally, motivated by the inherent ambiguity of building footprint extraction tasks, we systematically investigate alternative extraction paradigms and demonstrate that a combined approach of building masks and offsets achieves superior polygonal footprint results. Extensive experiments validate PolyFootNet's effectiveness, illustrating its promising potential as a robust, generalizable, and precise polygonal building footprint extraction method from challenging off-nadir imagery. To facilitate further research, we will release pre-trained weights of our offset prediction module at https://github.com/likaiucas/PolyFootNet.
Authors: Thanh-Dung Le, Vu Nguyen Ha, Ti Ti Nguyen, Geoffrey Eappen, Prabhu Thiruvasagam, Hong-fu Chou, Duc-Dung Tran, Hung Nguyen-Kha, Luis M. Garces-Socarras, Jorge L. Gonzalez-Rios, Juan Carlos Merlano-Duncan, Symeon Chatzinotas
Abstract: This study focuses on identifying the most effective pre-trained model for land use classification in onboard satellite processing, emphasizing achieving high accuracy, computational efficiency, and robustness against noisy data conditions commonly encountered during satellite-based inference. Through extensive experimentation, we compare the performance of traditional CNN-based, ResNet-based, and various pre-trained vision Transformer models. Our findings demonstrate that pre-trained Vision Transformer (ViT) models, particularly MobileViTV2 and EfficientViT-M2, outperform models trained from scratch in terms of accuracy and efficiency. These models achieve high performance with reduced computational requirements and exhibit greater resilience during inference under noisy conditions. While MobileViTV2 has excelled on clean validation data, EfficientViT-M2 has proved more robust when handling noise, making it the most suitable model for onboard satellite EO tasks. Our experimental results demonstrate that EfficientViT-M2 is the optimal choice for reliable and efficient RS-IC in satellite operations, achieving 98.76 % of accuracy, precision, and recall. Precisely, EfficientViT-M2 delivers the highest performance across all metrics, excels in training efficiency (1,000s) and inference time (10s), and demonstrates greater robustness (overall robustness score of 0.79). Consequently, EfficientViT-M2 consumes 63.93 % less power than MobileViTV2 (79.23 W) and 73.26 % less power than SwinTransformer (108.90 W). This highlights its significant advantage in energy efficiency.
Authors: Rongfeng Lu, Hangyu Chen, Zunjie Zhu, Yuhang Qin, Ming Lu, Le Zhang, Chenggang Yan, Anke Xue
Abstract: Thermography is especially valuable for the military and other users of surveillance cameras. Some recent methods based on Neural Radiance Fields (NeRF) are proposed to reconstruct the thermal scenes in 3D from a set of thermal and RGB images. However, unlike NeRF, 3D Gaussian splatting (3DGS) prevails due to its rapid training and real-time rendering. In this work, we propose ThermalGaussian, the first thermal 3DGS approach capable of rendering high-quality images in RGB and thermal modalities. We first calibrate the RGB camera and the thermal camera to ensure that both modalities are accurately aligned. Subsequently, we use the registered images to learn the multimodal 3D Gaussians. To prevent the overfitting of any single modality, we introduce several multimodal regularization constraints. We also develop smoothing constraints tailored to the physical characteristics of the thermal modality. Besides, we contribute a real-world dataset named RGBT-Scenes, captured by a hand-hold thermal-infrared camera, facilitating future research on thermal scene reconstruction. We conduct comprehensive experiments to show that ThermalGaussian achieves photorealistic rendering of thermal images and improves the rendering quality of RGB images. With the proposed multimodal regularization constraints, we also reduced the model's storage cost by 90%. Our project page is at https://thermalgaussian.github.io/.
Authors: Nimrod Shabtay, Felipe Maia Polo, Sivan Doveh, Wei Lin, M. Jehanzeb Mirza, Leshem Chosen, Mikhail Yurochkin, Yuekai Sun, Assaf Arbelle, Leonid Karlinsky, Raja Giryes
Abstract: The large-scale training of multi-modal models on data scraped from the web has shown outstanding utility in infusing these models with the required world knowledge to perform effectively on multiple downstream tasks. However, one downside of scraping data from the web can be the potential sacrifice of the benchmarks on which the abilities of these models are often evaluated. To safeguard against test data contamination and to truly test the abilities of these foundation models we propose LiveXiv: A scalable evolving live benchmark based on scientific ArXiv papers. LiveXiv accesses domain-specific manuscripts at any given timestamp and proposes to automatically generate visual question-answer pairs (VQA). This is done without any human-in-the-loop, using the multi-modal content in the manuscripts, like graphs, charts, and tables. Moreover, we introduce an efficient evaluation approach that estimates the performance of all models on the evolving benchmark using evaluations of only a subset of models. This significantly reduces the overall evaluation cost. We benchmark multiple open and proprietary Large Multi-modal Models (LMMs) on the first version of our benchmark, showing its challenging nature and exposing the models true abilities, avoiding contamination. Lastly, in our commitment to high quality, we have collected and evaluated a manually verified subset. By comparing its overall results to our automatic annotations, we have found that the performance variance is indeed minimal (<2.5%). Our dataset is available online on HuggingFace, and our code will be available here.
Authors: Baiqi Li, Zhiqiu Lin, Wenxuan Peng, Jean de Dieu Nyandwi, Daniel Jiang, Zixian Ma, Simran Khanuja, Ranjay Krishna, Graham Neubig, Deva Ramanan
Abstract: Vision-language models (VLMs) have made significant progress in recent visual-question-answering (VQA) benchmarks that evaluate complex visio-linguistic reasoning. However, are these models truly effective? In this work, we show that VLMs still struggle with natural images and questions that humans can easily answer, which we term natural adversarial samples. We also find it surprisingly easy to generate these VQA samples from natural image-text corpora using off-the-shelf models like CLIP and ChatGPT. We propose a semi-automated approach to collect a new benchmark, NaturalBench, for reliably evaluating VLMs with 10,000 human-verified VQA samples. Crucially, we adopt a $\textbf{vision-centric}$ design by pairing each question with two images that yield different answers, preventing blind solutions from answering without using the images. This makes NaturalBench more challenging than previous benchmarks that can be solved with commonsense priors. We evaluate 53 state-of-the-art VLMs on NaturalBench, showing that models like LLaVA-OneVision, Cambrian-1, Llama3.2-Vision, Molmo, Qwen2-VL, and even GPT-4o lag 50%-70% behind human performance (over 90%). We analyze why NaturalBench is hard from two angles: (1) Compositionality: Solving NaturalBench requires diverse visio-linguistic skills, including understanding attribute bindings, object relationships, and advanced reasoning like logic and counting. To this end, unlike prior work that uses a single tag per sample, we tag each NaturalBench sample with 1 to 8 skill tags for fine-grained evaluation. (2) Biases: NaturalBench exposes severe biases in VLMs, as models often choose the same answer regardless of the image. Lastly, we apply our benchmark curation method to diverse data sources, including long captions (over 100 words) and non-English languages like Chinese and Hindi, highlighting its potential for dynamic evaluations of VLMs.
Authors: Xinhao Liu, Jintong Li, Yicheng Jiang, Niranjan Sujay, Zhicheng Yang, Juexiao Zhang, John Abanes, Jing Zhang, Chen Feng
Abstract: Navigating dynamic urban environments presents significant challenges for embodied agents, requiring advanced spatial reasoning and adherence to common-sense norms. Despite progress, existing visual navigation methods struggle in map-free or off-street settings, limiting the deployment of autonomous agents like last-mile delivery robots. To overcome these obstacles, we propose a scalable, data-driven approach for human-like urban navigation by training agents on thousands of hours of in-the-wild city walking and driving videos sourced from the web. We introduce a simple and scalable data processing pipeline that extracts action supervision from these videos, enabling large-scale imitation learning without costly annotations. Our model learns sophisticated navigation policies to handle diverse challenges and critical scenarios. Experimental results show that training on large-scale, diverse datasets significantly enhances navigation performance, surpassing current methods. This work shows the potential of using abundant online video data to develop robust navigation policies for embodied agents in dynamic urban settings. Project homepage is at https://ai4ce.github.io/CityWalker/.
Authors: Lei Liu, Zhenghao Chen, Wei Jiang, Wei Wang, Dong Xu
Abstract: In this work, we propose a novel compression framework for 3D Gaussian Splatting (3DGS) data. Building on anchor-based 3DGS methodologies, our approach compresses all attributes within each anchor by introducing a novel Hybrid Entropy Model for 3D Gaussian Splatting (HEMGS) to achieve hybrid lossy-lossless compression. It consists of three main components: a variable-rate predictor, a hyperprior network, and an autoregressive network. First, unlike previous methods that adopt multiple models to achieve multi-rate lossy compression, thereby increasing training overhead, our variable-rate predictor enables variable-rate compression with a single model and a hyperparameter $\lambda$ by producing a learned Quantization Step feature for versatile lossy compression. Second, to improve lossless compression, the hyperprior network captures both scene-agnostic and scene-specific features to generate a prior feature, while the autoregressive network employs an adaptive context selection algorithm with flexible receptive fields to produce a contextual feature. By integrating these two features, HEMGS can accurately estimate the distribution of the current coding element within each attribute, enabling improved entropy coding and reduced storage. We integrate HEMGS into a compression framework, and experimental results on four benchmarks indicate that HEMGS achieves about a 40% average reduction in size while maintaining rendering quality over baseline methods and achieving state-of-the-art compression results.
Authors: Piotr Teterwak, Kuniaki Saito, Theodoros Tsiligkaridis, Bryan A. Plummer, Kate Saenko
Abstract: Multi-Source Domain Generalization (DG) is the task of training on multiple source domains and achieving high classification performance on unseen target domains. Recent methods combine robust features from web-scale pretrained backbones with new features learned from source data, and this has dramatically improved benchmark results. However, it remains unclear if DG finetuning methods are becoming better over time, or if improved benchmark performance is simply an artifact of stronger pre-training. Prior studies have shown that perceptual similarity to pre-training data correlates with zero-shot performance, but we find the effect limited in the DG setting. Instead, we posit that having perceptually similar data in pretraining is not enough; and that it is how well these data were learned that determines performance. This leads us to introduce the Alignment Hypothesis, which states that the final DG performance will be high if and only if alignment of image and class label text embeddings is high. Our experiments confirm the Alignment Hypothesis is true, and we use it as an analysis tool of existing DG methods evaluated on DomainBed datasets by splitting evaluation data into In-pretraining (IP) and Out-of-pretraining (OOP). We show that all evaluated DG methods struggle on DomainBed-OOP, while recent methods excel on DomainBed-IP. Put together, our findings highlight the need for DG methods which can generalize beyond pretraining alignment.
Authors: Chengbo Wang, Guozheng Ma, Yifei Xue, Yizhen Lao
Abstract: 3D Gaussian Splatting (3DGS) has emerged as a powerful technique for novel view synthesis, demonstrating remarkable capability in high-fidelity scene reconstruction through its Gaussian primitive representations. However, the computational overhead induced by the massive number of primitives poses a significant bottleneck to training efficiency. To overcome this challenge, we propose Group Training, a simple yet effective strategy that organizes Gaussian primitives into manageable groups, optimizing training efficiency and improving rendering quality. This approach shows universal compatibility with existing 3DGS frameworks, including vanilla 3DGS and Mip-Splatting, consistently achieving accelerated training while maintaining superior synthesis quality. Extensive experiments reveal that our straightforward Group Training strategy achieves up to 30% faster convergence and improved rendering quality across diverse scenarios.
Authors: Haotong Lin, Sida Peng, Jingxiao Chen, Songyou Peng, Jiaming Sun, Minghuan Liu, Hujun Bao, Jiashi Feng, Xiaowei Zhou, Bingyi Kang
Abstract: Prompts play a critical role in unleashing the power of language and vision foundation models for specific tasks. For the first time, we introduce prompting into depth foundation models, creating a new paradigm for metric depth estimation termed Prompt Depth Anything. Specifically, we use a low-cost LiDAR as the prompt to guide the Depth Anything model for accurate metric depth output, achieving up to 4K resolution. Our approach centers on a concise prompt fusion design that integrates the LiDAR at multiple scales within the depth decoder. To address training challenges posed by limited datasets containing both LiDAR depth and precise GT depth, we propose a scalable data pipeline that includes synthetic data LiDAR simulation and real data pseudo GT depth generation. Our approach sets new state-of-the-arts on the ARKitScenes and ScanNet++ datasets and benefits downstream applications, including 3D reconstruction and generalized robotic grasping.
Authors: Sagnik Majumder, Tushar Nagarajan, Ziad Al-Halah, Kristen Grauman
Abstract: We introduce SWITCH-A-VIEW, a model that learns to automatically select the viewpoint to display at each timepoint when creating a how-to video. The key insight of our approach is how to train such a model from unlabeled -- but human-edited -- video samples. We pose a pretext task that pseudo-labels segments in the training videos for their primary viewpoint (egocentric or exocentric), and then discovers the patterns between the visual and spoken content in a how-to video on the one hand and its view-switch moments on the other hand. Armed with this predictor, our model can be applied to new multi-view video settings for orchestrating which viewpoint should be displayed when, even when such settings come with limited labels. We demonstrate our idea on a variety of real-world videos from HowTo100M and Ego-Exo4D, and rigorously validate its advantages. Project: https://vision.cs.utexas.edu/projects/switch_a_view/.
Authors: Jing Li, Bo Wang
Abstract: Recent advancements in scene text spotting have focused on end-to-end methodologies that heavily rely on precise location annotations, which are often costly and labor-intensive to procure. In this study, we introduce an innovative approach that leverages only transcription annotations for training text spotting models, substantially reducing the dependency on elaborate annotation processes. Our methodology employs a query-based paradigm that facilitates the learning of implicit location features through the interaction between text queries and image embeddings. These features are later refined during the text recognition phase using an attention activation map. Addressing the challenges associated with training a weakly-supervised model from scratch, we implement a circular curriculum learning strategy to enhance model convergence. Additionally, we introduce a coarse-to-fine cross-attention localization mechanism for more accurate text instance localization. Notably, our framework supports audio-based annotation, which significantly diminishes annotation time and provides an inclusive alternative for individuals with disabilities. Our approach achieves competitive performance against existing benchmarks, demonstrating that high accuracy in text spotting can be attained without extensive location annotations.
Authors: Bin Wang, Li Jing
Abstract: Text recognition technology applied to street-view storefront signs is increasingly utilized across various practical domains, including map navigation, smart city planning analysis, and business value assessments in commercial districts. This technology holds significant research and commercial potential. Nevertheless, it faces numerous challenges. Street view images often contain signboards with complex designs and diverse text styles, complicating the text recognition process. A notable advancement in this field was introduced by our team in a recent competition. We developed a novel multistage approach that integrates multimodal feature fusion, extensive self-supervised training, and a Transformer-based large model. Furthermore, innovative techniques such as BoxDQN, which relies on reinforcement learning, and text rectification methods were employed, leading to impressive outcomes. Comprehensive experiments have validated the effectiveness of these methods, showcasing our potential to enhance text recognition capabilities in complex urban environments.
Authors: Alexandru Buburuzan, Anuj Sharma, John Redford, Puneet K. Dokania, Romain Mueller
Abstract: Safety-critical applications, such as autonomous driving, require extensive multimodal data for rigorous testing. Methods based on synthetic data are gaining prominence due to the cost and complexity of gathering real-world data but require a high degree of realism and controllability in order to be useful. This paper introduces MObI, a novel framework for Multimodal Object Inpainting that leverages a diffusion model to create realistic and controllable object inpaintings across perceptual modalities, demonstrated for both camera and lidar simultaneously. Using a single reference RGB image, MObI enables objects to be seamlessly inserted into existing multimodal scenes at a 3D location specified by a bounding box, while maintaining semantic consistency and multimodal coherence. Unlike traditional inpainting methods that rely solely on edit masks, our 3D bounding box conditioning gives objects accurate spatial positioning and realistic scaling. As a result, our approach can be used to insert novel objects flexibly into multimodal scenes, providing significant advantages for testing perception models.
Authors: Dana A Abdullah, Dana Rasul Hamad, Ismail Y. Maolood, Hakem Beitollahi, Aso K. Ameen, Sirwan A. Aula, Abdulhady Abas Abdulla, Mohammed Y. Shakorf, Sabat Salih Muhamad
Abstract: Recognizing the same faces with and without masks is important for ensuring consistent identification in security, access control, and public safety. This capability is crucial in scenarios like law enforcement, healthcare, and surveillance, where accurate recognition must be maintained despite facial occlusion. This research focuses on the challenge of recognizing the same faces with and without masks by employing cosine similarity as the primary technique. With the increased use of masks, traditional facial recognition systems face significant accuracy issues, making it crucial to develop methods that can reliably identify individuals in masked conditions. For that reason, this study proposed Masked-Unmasked Face Matching Model (MUFM). This model employs transfer learning using the Visual Geometry Group (VGG16) model to extract significant facial features, which are subsequently classified utilizing the K-Nearest Neighbors (K-NN) algorithm. The cosine similarity metric is employed to compare masked and unmasked faces of the same individuals. This approach represents a novel contribution, as the task of recognizing the same individual with and without a mask using cosine similarity has not been previously addressed. By integrating these advanced methodologies, the research demonstrates effective identification of individuals despite the presence of masks, addressing a significant limitation in traditional systems. Using data is another essential part of this work, by collecting and preparing an image dataset from three different sources especially some of those data are real provided a comprehensive power of this research. The image dataset used were already collected in three different datasets of masked and unmasked for the same faces.
Authors: Dhruv Parikh, Jacob Fein-Ashley, Tian Ye, Rajgopal Kannan, Viktor Prasanna
Abstract: Convolutional Neural Networks (CNN) and Vision Transformers (ViT) have dominated the field of Computer Vision (CV). Graph Neural Networks (GNN) have performed remarkably well across diverse domains because they can represent complex relationships via unstructured graphs. However, the applicability of GNNs for visual tasks was unexplored till the introduction of Vision GNNs (ViG). Despite the success of ViGs, their performance is severely bottlenecked due to the expensive $k$-Nearest Neighbors ($k$-NN) based graph construction. Recent works addressing this bottleneck impose constraints on the flexibility of GNNs to build unstructured graphs, undermining their core advantage while introducing additional inefficiencies. To address these issues, in this paper, we propose a novel method called Dynamic Efficient Graph Convolution (DEGC) for designing efficient and globally aware ViGs. DEGC partitions the input image and constructs graphs in parallel for each partition, improving graph construction efficiency. Further, DEGC integrates local intra-graph and global inter-graph feature learning, enabling enhanced global context awareness. Using DEGC as a building block, we propose a novel CNN-GNN architecture, ClusterViG, for CV tasks. Extensive experiments indicate that ClusterViG reduces end-to-end inference latency for vision tasks by up to $5\times$ when compared against a suite of models such as ViG, ViHGNN, PVG, and GreedyViG, with a similar model parameter count. Additionally, ClusterViG reaches state-of-the-art performance on image classification, object detection, and instance segmentation tasks, demonstrating the effectiveness of the proposed globally aware learning strategy. Finally, input partitioning performed by DEGC enables ClusterViG to be trained efficiently on higher-resolution images, underscoring the scalability of our approach.
Authors: Yu Pan, Bingrong Dai, Jiahao Chen, Lin Wang, Yi Du, Jiao Liu
Abstract: In recent years, Diffusion Models (DMs) have demonstrated significant advances in the field of image generation. However, according to current research, DMs are vulnerable to backdoor attacks, which allow attackers to control the model's output by inputting data containing covert triggers, such as a specific visual patch or phrase. Existing defense strategies are well equipped to thwart such attacks through backdoor detection and trigger inversion because previous attack methods are constrained by limited input spaces and low-dimensional triggers. For example, visual triggers are easily observed by defenders, text-based or attention-based triggers are more susceptible to neural network detection. To explore more possibilities of backdoor attack in DMs, we propose Gungnir, a novel method that enables attackers to activate the backdoor in DMs through style triggers within input images. Our approach proposes using stylistic features as triggers for the first time and implements backdoor attacks successfully in image-to-image tasks by introducing Reconstructing-Adversarial Noise (RAN) and Short-Term Timesteps-Retention (STTR). Our technique generates trigger-embedded images that are perceptually indistinguishable from clean images, thus bypassing both manual inspection and automated detection neural networks. Experiments demonstrate that Gungnir can easily bypass existing defense methods. Among existing DM defense frameworks, our approach achieves a 0 backdoor detection rate (BDR). Our codes are available at https://github.com/paoche11/Gungnir.
Authors: Ruofan Wang, Xiang Zheng, Xiaosen Wang, Cong Wang, Xingjun Ma
Abstract: The growing deployment of large Vision-Language Models (VLMs) exposes critical safety gaps in their alignment mechanisms. While existing jailbreak studies primarily focus on VLMs' susceptibility to harmful instructions, we reveal a fundamental yet overlooked vulnerability: toxic text continuation, where VLMs produce highly toxic completions when prompted with harmful text prefixes paired with semantically adversarial images. To systematically study this threat, we propose Red Team Diffuser (RTD), the first red teaming diffusion model that coordinates adversarial image generation and toxic continuation through reinforcement learning. Our key innovations include dynamic cross-modal attack and stealth-aware optimization. For toxic text prefixes from an LLM safety benchmark, we conduct greedy search to identify optimal image prompts that maximally induce toxic completions. The discovered image prompts then drive RL-based diffusion model fine-tuning, producing semantically aligned adversarial images that boost toxicity rates. Stealth-aware optimization introduces joint adversarial rewards that balance toxicity maximization (via Detoxify classifier) and stealthiness (via BERTScore), circumventing traditional noise-based adversarial patterns. Experimental results demonstrate the effectiveness of RTD, increasing the toxicity rate of LLaVA outputs by 10.69% over text-only baselines on the original attack set and 8.91% on an unseen set, proving generalization capability. Moreover, RTD exhibits strong cross-model transferability, raising the toxicity rate by 5.1% on Gemini and 26.83% on LLaMA. Our findings expose two critical flaws in current VLM alignment: (1) failure to prevent toxic continuation from harmful prefixes, and (2) overlooking cross-modal attack vectors. These results necessitate a paradigm shift toward multimodal red teaming in safety evaluations.
Authors: Size Wu, Wenwei Zhang, Lumin Xu, Sheng Jin, Zhonghua Wu, Qingyi Tao, Wentao Liu, Wei Li, Chen Change Loy
Abstract: Unifying visual understanding and generation within a single multimodal framework remains a significant challenge, as the two inherently heterogeneous tasks require representations at different levels of granularity. Current approaches that utilize vector quantization (VQ) or variational autoencoders (VAE) for unified visual representation prioritize intrinsic imagery features over semantics, compromising understanding performance. In this work, we take inspiration from masked image modelling (MIM) that learns rich semantics via a mask-and-reconstruct pre-training and its successful extension to masked autoregressive (MAR) image generation. A preliminary study on the MAR encoder's representation reveals exceptional linear probing accuracy and precise feature response to visual concepts, which indicates MAR's potential for visual understanding tasks beyond its original generation role. Based on these insights, we present \emph{Harmon}, a unified autoregressive framework that harmonizes understanding and generation tasks with a shared MAR encoder. Through a three-stage training procedure that progressively optimizes understanding and generation capabilities, Harmon achieves state-of-the-art image generation results on the GenEval, MJHQ30K and WISE benchmarks while matching the performance of methods with dedicated semantic encoders (e.g., Janus) on image understanding benchmarks. Our code and models will be available at https://github.com/wusize/Harmon.
Authors: Van Nguyen Nguyen, Stephen Tyree, Andrew Guo, Mederic Fourmy, Anas Gouda, Taeyeop Lee, Sungphill Moon, Hyeontae Son, Lukas Ranftl, Jonathan Tremblay, Eric Brachmann, Bertram Drost, Vincent Lepetit, Carsten Rother, Stan Birchfield, Jiri Matas, Yann Labbe, Martin Sundermeyer, Tomas Hodan
Abstract: We present the evaluation methodology, datasets and results of the BOP Challenge 2024, the 6th in a series of public competitions organized to capture the state of the art in 6D object pose estimation and related tasks. In 2024, our goal was to transition BOP from lab-like setups to real-world scenarios. First, we introduced new model-free tasks, where no 3D object models are available and methods need to onboard objects just from provided reference videos. Second, we defined a new, more practical 6D object detection task where identities of objects visible in a test image are not provided as input. Third, we introduced new BOP-H3 datasets recorded with high-resolution sensors and AR/VR headsets, closely resembling real-world scenarios. BOP-H3 include 3D models and onboarding videos to support both model-based and model-free tasks. Participants competed on seven challenge tracks. Notably, the best 2024 method for model-based 6D localization of unseen objects (FreeZeV2.1) achieves 22% higher accuracy on BOP-Classic-Core than the best 2023 method (GenFlow), and is only 4% behind the best 2023 method for seen objects (GPose2023) although being significantly slower (24.9 vs 2.7s per image). A more practical 2024 method for this task is Co-op which takes only 0.8s per image and is 13% more accurate than GenFlow. Methods have similar rankings on 6D detection as on 6D localization but higher run time. On model-based 2D detection of unseen objects, the best 2024 method (MUSE) achieves 21--29% relative improvement compared to the best 2023 method (CNOS). However, the 2D detection accuracy for unseen objects is still -35% behind the accuracy for seen objects (GDet2023), and the 2D detection stage is consequently the main bottleneck of existing pipelines for 6D localization/detection of unseen objects. The online evaluation system stays open and is available at http://bop.felk.cvut.cz/
URLs: http://bop.felk.cvut.cz/
Authors: Davide Sferrazza, Gabriele Berton, Gabriele Trivigno, Carlo Masone
Abstract: Visual Place Recognition (VPR) is a critical task in computer vision, traditionally enhanced by re-ranking retrieval results with image matching. However, recent advancements in VPR methods have significantly improved performance, challenging the necessity of re-ranking. In this work, we show that modern retrieval systems often reach a point where re-ranking can degrade results, as current VPR datasets are largely saturated. We propose using image matching as a verification step to assess retrieval confidence, demonstrating that inlier counts can reliably predict when re-ranking is beneficial. Our findings shift the paradigm of retrieval pipelines, offering insights for more robust and adaptive VPR systems. The code is available at https://github.com/FarInHeight/To-Match-or-Not-to-Match.
URLs: https://github.com/FarInHeight/To-Match-or-Not-to-Match.
Authors: Shuangfan Zhou, Chu Zhou, Youwei Lyu, Heng Guo, Zhanyu Ma, Boxin Shi, Imari Sato
Abstract: Polarization cameras can capture multiple polarized images with different polarizer angles in a single shot, bringing convenience to polarization-based downstream tasks. However, their direct outputs are color-polarization filter array (CPFA) raw images, requiring demosaicing to reconstruct full-resolution, full-color polarized images; unfortunately, this necessary step introduces artifacts that make polarization-related parameters such as the degree of polarization (DoP) and angle of polarization (AoP) prone to error. Besides, limited by the hardware design, the resolution of a polarization camera is often much lower than that of a conventional RGB camera. Existing polarized image demosaicing (PID) methods are limited in that they cannot enhance resolution, while polarized image super-resolution (PISR) methods, though designed to obtain high-resolution (HR) polarized images from the demosaicing results, tend to retain or even amplify errors in the DoP and AoP introduced by demosaicing artifacts. In this paper, we propose PIDSR, a joint framework that performs complementary Polarized Image Demosaicing and Super-Resolution, showing the ability to robustly obtain high-quality HR polarized images with more accurate DoP and AoP from a CPFA raw image in a direct manner. Experiments show our PIDSR not only achieves state-of-the-art performance on both synthetic and real data, but also facilitates downstream tasks.
Authors: Lin Zhu, Xinbing Wang, Chenghu Zhou, Nanyang Ye
Abstract: Recent advances in large pre-trained models showed promising results in few-shot learning. However, their generalization ability on two-dimensional Out-of-Distribution (OoD) data, i.e., correlation shift and diversity shift, has not been thoroughly investigated. Researches have shown that even with a significant amount of training data, few methods can achieve better performance than the standard empirical risk minimization method (ERM) in OoD generalization. This few-shot OoD generalization dilemma emerges as a challenging direction in deep neural network generalization research, where the performance suffers from overfitting on few-shot examples and OoD generalization errors. In this paper, leveraging a broader supervision source, we explore a novel Bayesian cross-modal image-text alignment learning method (Bayes-CAL) to address this issue. Specifically, the model is designed as only text representations are fine-tuned via a Bayesian modelling approach with gradient orthogonalization loss and invariant risk minimization (IRM) loss. The Bayesian approach is essentially introduced to avoid overfitting the base classes observed during training and improve generalization to broader unseen classes. The dedicated loss is introduced to achieve better image-text alignment by disentangling the causal and non-casual parts of image features. Numerical experiments demonstrate that Bayes-CAL achieved state-of-the-art OoD generalization performances on two-dimensional distribution shifts. Moreover, compared with CLIP-like models, Bayes-CAL yields more stable generalization performances on unseen classes. Our code is available at https://github.com/LinLLLL/BayesCAL.
Authors: Pengxiao Han, Changkun Ye, Jinguang Tong, Cuicui Jiang, Jie Hong, Li Fang, Xuesong Li
Abstract: Language-based foundation models, such as large language models (LLMs) or large vision-language models (LVLMs), have been widely studied in long-tailed recognition. However, the need for linguistic data is not applicable to all practical tasks. In this study, we aim to explore using large vision models (LVMs) or visual foundation models (VFMs) to enhance long-tailed data features without any language information. Specifically, we extract features from the LVM and fuse them with features in the baseline network's map and latent space to obtain the augmented features. Moreover, we design several prototype-based losses in the latent space to further exploit the potential of the augmented features. In the experimental section, we validate our approach on two benchmark datasets: ImageNet-LT and iNaturalist2018.
Authors: Yihang Liu, Lianghua He, Ying Wen, Longzhen Yang, Hongzhou Chen
Abstract: Current self-supervised methods, such as contrastive learning, predominantly focus on global discrimination, neglecting the critical fine-grained anatomical details required for accurate radiographic analysis. To address this challenge, we propose an Anatomy-driven self-supervised framework for enhancing Fine-grained Representation in radiographic image analysis (AFiRe). The core idea of AFiRe is to align the anatomical consistency with the unique token-processing characteristics of Vision Transformer. Specifically, AFiRe synergistically performs two self-supervised schemes: (i) Token-wise anatomy-guided contrastive learning, which aligns image tokens based on structural and categorical consistency, thereby enhancing fine-grained spatial-anatomical discrimination; (ii) Pixel-level anomaly-removal restoration, which particularly focuses on local anomalies, thereby refining the learned discrimination with detailed geometrical information. Additionally, we propose Synthetic Lesion Mask to enhance anatomical diversity while preserving intra-consistency, which is typically corrupted by traditional data augmentations, such as Cropping and Affine transformations. Experimental results show that AFiRe: (i) provides robust anatomical discrimination, achieving more cohesive feature clusters compared to state-of-the-art contrastive learning methods; (ii) demonstrates superior generalization, surpassing 7 radiography-specific self-supervised methods in multi-label classification tasks with limited labeling; and (iii) integrates fine-grained information, enabling precise anomaly detection using only image-level annotations.
Authors: Xiaojun Ye, Chun Wang, Yiren Song, Sheng Zhou, Liangcheng Li, Jiajun Bu
Abstract: Movie Audio Description (AD) aims to narrate visual content during dialogue-free segments, particularly benefiting blind and visually impaired (BVI) audiences. Compared with general video captioning, AD demands plot-relevant narration with explicit character name references, posing unique challenges in movie understanding.To identify active main characters and focus on storyline-relevant regions, we propose FocusedAD, a novel framework that delivers character-centric movie audio descriptions. It includes: (i) a Character Perception Module(CPM) for tracking character regions and linking them to names; (ii) a Dynamic Prior Module(DPM) that injects contextual cues from prior ADs and subtitles via learnable soft prompts; and (iii) a Focused Caption Module(FCM) that generates narrations enriched with plot-relevant details and named characters. To overcome limitations in character identification, we also introduce an automated pipeline for building character query banks. FocusedAD achieves state-of-the-art performance on multiple benchmarks, including strong zero-shot results on MAD-eval-Named and our newly proposed Cinepile-AD dataset. Code and data will be released at https://github.com/Thorin215/FocusedAD .
Authors: Le Wang, Zonghao Ying, Tianyuan Zhang, Siyuan Liang, Shengshan Hu, Mingchuan Zhang, Aishan Liu, Xianglong Liu
Abstract: The emergence of multimodal large language models has redefined the agent paradigm by integrating language and vision modalities with external data sources, enabling agents to better interpret human instructions and execute increasingly complex tasks. However, in this work, we identify a critical yet previously overlooked security vulnerability in multimodal agents: cross-modal prompt injection attacks. To exploit this vulnerability, we propose CrossInject, a novel attack framework in which attackers embed adversarial perturbations across multiple modalities to align with target malicious content, allowing external instructions to hijack the agent's decision-making process and execute unauthorized tasks. Our approach consists of two key components. First, we introduce Visual Latent Alignment, where we optimize adversarial features to the malicious instructions in the visual embedding space based on a text-to-image generative model, ensuring that adversarial images subtly encode cues for malicious task execution. Subsequently, we present Textual Guidance Enhancement, where a large language model is leveraged to infer the black-box defensive system prompt through adversarial meta prompting and generate an malicious textual command that steers the agent's output toward better compliance with attackers' requests. Extensive experiments demonstrate that our method outperforms existing injection attacks, achieving at least a +26.4% increase in attack success rates across diverse tasks. Furthermore, we validate our attack's effectiveness in real-world multimodal autonomous agents, highlighting its potential implications for safety-critical applications.
Authors: Zhenkui Yang, Zeyi Huang, Ge Wang, Han Ding, Tony Xiao Han, Fei Wang
Abstract: Wireless signal-based human sensing technologies, such as WiFi, millimeter-wave (mmWave) radar, and Radio Frequency Identification (RFID), enable the detection and interpretation of human presence, posture, and activities, thereby providing critical support for applications in public security, healthcare, and smart environments. These technologies exhibit notable advantages due to their non-contact operation and environmental adaptability; however, existing systems often fail to leverage the textual information inherent in datasets. To address this, we propose an innovative text-enhanced wireless sensing framework, WiTalk, that seamlessly integrates semantic knowledge through three hierarchical prompt strategies-label-only, brief description, and detailed action description-without requiring architectural modifications or incurring additional data costs. We rigorously validate this framework across three public benchmark datasets: XRF55 for human action recognition (HAR), and WiFiTAL and XRFV2 for WiFi temporal action localization (TAL). Experimental results demonstrate significant performance improvements: on XRF55, accuracy for WiFi, RFID, and mmWave increases by 3.9%, 2.59%, and 0.46%, respectively; on WiFiTAL, the average performance of WiFiTAD improves by 4.98%; and on XRFV2, the mean average precision gains across various methods range from 4.02% to 13.68%. Our codes have been included in https://github.com/yangzhenkui/WiTalk.
Authors: Jing Zhang, Dan Guo, Zhangbin Li, Meng Wang
Abstract: This paper focuses on a key challenge in visual art understanding: given an art image, the model pinpoints pixel regions that trigger a specific human emotion, and generates linguistic explanations for the emotional arousal. Despite recent advances in art understanding, pixel-level emotion understanding still faces a dual challenge: first, the subjectivity of emotion makes it difficult for general segmentation models like SAM to adapt to emotion-oriented segmentation tasks; and second, the abstract nature of art expression makes it difficult for captioning models to balance pixel-level semantic understanding and emotion reasoning. To solve the above problems, this paper proposes the Emotion stimuli Segmentation and Explanation Model (EmoSEM) to endow the segmentation model SAM with emotion comprehension capability. First, to enable the model to perform segmentation under the guidance of emotional intent well, we introduce an emotional prompt with a learnable mask token as the conditional input for segmentation decoding. Then, we design an emotion projector to establish the association between emotion and visual features. Next, more importantly, to address emotion-visual stimuli alignment, we develop a lightweight prefix projector, a module that fuses the learned emotional mask with the corresponding emotion into a unified representation compatible with the language model. Finally, we input the joint visual, mask, and emotional tokens into the language model and output the emotional explanations. It ensures that the generated interpretations remain semantically and emotionally coherent with the visual stimuli. The method innovatively realizes end-to-end modeling from low-level pixel features to high-level emotion interpretation, providing the first interpretable fine-grained analysis framework for artistic emotion computing. Extensive experiments validate the effectiveness of our model.
Authors: Shiben Liu, Huijie Fan, Qiang Wang, Baojie Fan, Yandong Tang, Liangqiong Qu
Abstract: Lifelong Person Re-identification (LReID) suffers from a key challenge in preserving old knowledge while adapting to new information. The existing solutions include rehearsal-based and rehearsal-free methods to address this challenge. Rehearsal-based approaches rely on knowledge distillation, continuously accumulating forgetting during the distillation process. Rehearsal-free methods insufficiently learn the distribution of each domain, leading to forgetfulness over time. To solve these issues, we propose a novel Distribution-aware Forgetting Compensation (DAFC) model that explores cross-domain shared representation learning and domain-specific distribution integration without using old exemplars or knowledge distillation. We propose a Text-driven Prompt Aggregation (TPA) that utilizes text features to enrich prompt elements and guide the prompt model to learn fine-grained representations for each instance. This can enhance the differentiation of identity information and establish the foundation for domain distribution awareness. Then, Distribution-based Awareness and Integration (DAI) is designed to capture each domain-specific distribution by a dedicated expert network and adaptively consolidate them into a shared region in high-dimensional space. In this manner, DAI can consolidate and enhance cross-domain shared representation learning while alleviating catastrophic forgetting. Furthermore, we develop a Knowledge Consolidation Mechanism (KCM) that comprises instance-level discrimination and cross-domain consistency alignment strategies to facilitate model adaptive learning of new knowledge from the current domain and promote knowledge consolidation learning between acquired domain-specific distributions, respectively. Experimental results show that our DAFC outperforms state-of-the-art methods. Our code is available at https://github.com/LiuShiBen/DAFC.
Authors: Mingxia Zhan, Li Zhang, Xiaomeng Chu, Beibei Wang
Abstract: Monocular depth estimation (MDE) aims to predict per-pixel depth values from a single RGB image. Recent advancements have positioned diffusion models as effective MDE tools by framing the challenge as a conditional image generation task. Despite their progress, these methods often struggle with accurately reconstructing distant depths, due largely to the imbalanced distribution of depth values and an over-reliance on spatial-domain features. To overcome these limitations, we introduce VistaDepth, a novel framework that integrates adaptive frequency-domain feature enhancements with an adaptive weight-balancing mechanism into the diffusion process. Central to our approach is the Latent Frequency Modulation (LFM) module, which dynamically refines spectral responses in the latent feature space, thereby improving the preservation of structural details and reducing noisy artifacts. Furthermore, we implement an adaptive weighting strategy that modulates the diffusion loss in real-time, enhancing the model's sensitivity towards distant depth reconstruction. These innovations collectively result in superior depth perception performance across both distance and detail. Experimental evaluations confirm that VistaDepth achieves state-of-the-art performance among diffusion-based MDE techniques, particularly excelling in the accurate reconstruction of distant regions.
Authors: Hongchi Xia, Entong Su, Marius Memmel, Arhan Jain, Raymond Yu, Numfor Mbiziwo-Tiapo, Ali Farhadi, Abhishek Gupta, Shenlong Wang, Wei-Chiu Ma
Abstract: Creating virtual digital replicas from real-world data unlocks significant potential across domains like gaming and robotics. In this paper, we present DRAWER, a novel framework that converts a video of a static indoor scene into a photorealistic and interactive digital environment. Our approach centers on two main contributions: (i) a reconstruction module based on a dual scene representation that reconstructs the scene with fine-grained geometric details, and (ii) an articulation module that identifies articulation types and hinge positions, reconstructs simulatable shapes and appearances and integrates them into the scene. The resulting virtual environment is photorealistic, interactive, and runs in real time, with compatibility for game engines and robotic simulation platforms. We demonstrate the potential of DRAWER by using it to automatically create an interactive game in Unreal Engine and to enable real-to-sim-to-real transfer for robotics applications.
Authors: Yingtai Li, Xueming Fu, Han Li, Shang Zhao, Ruiyang Jin, S. Kevin Zhou
Abstract: Sparse-view computed tomography (CT) reduces radiation exposure by acquiring fewer projections, making it a valuable tool in clinical scenarios where low-dose radiation is essential. However, this often results in increased noise and artifacts due to limited data. In this paper we propose a novel 3D Gaussian representation (3DGR) based method for sparse-view CT reconstruction. Inspired by recent success in novel view synthesis driven by 3D Gaussian splatting, we leverage the efficiency and expressiveness of 3D Gaussian representation as an alternative to implicit neural representation. To unleash the potential of 3DGR for CT imaging scenario, we propose two key innovations: (i) FBP-image-guided Guassian initialization and (ii) efficient integration with a differentiable CT projector. Extensive experiments and ablations on diverse datasets demonstrate the proposed 3DGR-CT consistently outperforms state-of-the-art counterpart methods, achieving higher reconstruction accuracy with faster convergence. Furthermore, we showcase the potential of 3DGR-CT for real-time physical simulation, which holds important clinical applications while challenging for implicit neural representations.
Authors: Kazuki Sakamoto, Connor T. Jerzak, Adel Daoud
Abstract: Earth observation (EO) data such as satellite imagery can have far-reaching impacts on our understanding of the geography of poverty, especially when coupled with machine learning (ML) and computer vision. Early research used computer vision to predict living conditions in areas with limited data, but recent studies increasingly focus on causal analysis. Despite this shift, the use of EO-ML methods for causal inference lacks thorough documentation, and best practices are still developing. Through a comprehensive scoping review, we catalog the current literature on EO-ML methods in causal analysis. We synthesize five principal approaches to incorporating EO data in causal workflows: (1) outcome imputation for downstream causal analysis, (2) EO image deconfounding, (3) EO-based treatment effect heterogeneity, (4) EO-based transportability analysis, and (5) image-informed causal discovery. Building on these findings, we provide a detailed protocol guiding researchers in integrating EO data into causal analysis -- covering data requirements, computer vision model selection, and evaluation metrics. While our focus centers on health and living conditions outcomes, our protocol is adaptable to other sustainable development domains utilizing EO data.
Authors: Songcheng Du, Yang Zou, Zixu Wang, Xingyuan Li, Ying Li, Changjing Shang, Qiang Shen
Abstract: Hyperspectral and Multispectral Image Fusion (HMIF) aims to fuse low-resolution hyperspectral images (LR-HSIs) and high-resolution multispectral images (HR-MSIs) to reconstruct high spatial and high spectral resolution images. Current methods typically apply direct fusion from the two modalities without effective supervision, leading to an incomplete perception of deep modality-complementary information and a limited understanding of inter-modality correlations. To address these issues, we propose a simple yet effective solution for unsupervised HMIF, revealing that modality decoupling is key to improving fusion performance. Specifically, we propose an end-to-end self-supervised \textbf{Mo}dality-Decoupled \textbf{S}patial-\textbf{S}pectral Fusion (\textbf{MossFuse}) framework that decouples shared and complementary information across modalities and aggregates a concise representation of both LR-HSIs and HR-MSIs to reduce modality redundancy. Also, we introduce the subspace clustering loss as a clear guide to decouple modality-shared features from modality-complementary ones. Systematic experiments over multiple datasets demonstrate that our simple and effective approach consistently outperforms the existing HMIF methods while requiring considerably fewer parameters with reduced inference time. The anonymous source code is in \href{https://github.com/dusongcheng/MossFuse}{MossFuse}.
Authors: Kaizhen Sun, Jinghang Li, Kuan Dai, Bangyan Liao, Wei Xiong, Yi Zhou
Abstract: Time-to-Collision (TTC) estimation lies in the core of the forward collision warning (FCW) functionality, which is key to all Automatic Emergency Braking (AEB) systems. Although the success of solutions using frame-based cameras (e.g., Mobileye's solutions) has been witnessed in normal situations, some extreme cases, such as the sudden variation in the relative speed of leading vehicles and the sudden appearance of pedestrians, still pose significant risks that cannot be handled. This is due to the inherent imaging principles of frame-based cameras, where the time interval between adjacent exposures introduces considerable system latency to AEB. Event cameras, as a novel bio-inspired sensor, offer ultra-high temporal resolution and can asynchronously report brightness changes at the microsecond level. To explore the potential of event cameras in the above-mentioned challenging cases, we propose EvTTC, which is, to the best of our knowledge, the first multi-sensor dataset focusing on TTC tasks under high-relative-speed scenarios. EvTTC consists of data collected using standard cameras and event cameras, covering various potential collision scenarios in daily driving and involving multiple collision objects. Additionally, LiDAR and GNSS/INS measurements are provided for the calculation of ground-truth TTC. Considering the high cost of testing TTC algorithms on full-scale mobile platforms, we also provide a small-scale TTC testbed for experimental validation and data augmentation. All the data and the design of the testbed are open sourced, and they can serve as a benchmark that will facilitate the development of vision-based TTC techniques.
Authors: Lars Kr\"oger, Cristian Cioflan, Victor Kartsch, Luca Benini
Abstract: RISC-V-based architectures are paving the way for efficient On-Device Learning (ODL) in smart edge devices. When applied across multiple nodes, ODL enables the creation of intelligent sensor networks that preserve data privacy. However, developing ODL-capable, battery-operated embedded platforms presents significant challenges due to constrained computational resources and limited device lifetime, besides intrinsic learning issues such as catastrophic forgetting. We face these challenges by proposing a regularization-based On-Device Federated Continual Learning algorithm tailored for multiple nano-drones performing face recognition tasks. We demonstrate our approach on a RISC-V-based 10-core ultra-low-power SoC, optimizing the ODL computational requirements. We improve the classification accuracy by 24% over naive fine-tuning, requiring 178 ms per local epoch and 10.5 s per global epoch, demonstrating the effectiveness of the architecture for this task.
Authors: Hye-Min Won, Jieun Lee, Jiyong Oh
Abstract: Reliable localization is critical for robot navigation in complex indoor environments. In this paper, we propose an uncertainty-aware localization method that enhances the reliability of localization outputs without modifying the prediction model itself. This study introduces a percentile-based rejection strategy that filters out unreliable 3-DoF pose predictions based on aleatoric and epistemic uncertainties the network estimates. We apply this approach to a multi-modal end-to-end localization that fuses RGB images and 2D LiDAR data, and we evaluate it across three real-world datasets collected using a commercialized serving robot. Experimental results show that applying stricter uncertainty thresholds consistently improves pose accuracy. Specifically, the mean position error is reduced by 41.0%, 56.7%, and 69.4%, and the mean orientation error by 55.6%, 65.7%, and 73.3%, when applying 90%, 80%, and 70% thresholds, respectively. Furthermore, the rejection strategy effectively removes extreme outliers, resulting in better alignment with ground truth trajectories. To the best of our knowledge, this is the first study to quantitatively demonstrate the benefits of percentile-based uncertainty rejection in multi-modal end-to-end localization tasks. Our approach provides a practical means to enhance the reliability and accuracy of localization systems in real-world deployments.
Authors: Yilin Liu, Duoteng Xu, Xingyao Yu, Xiang Xu, Daniel Cohen-Or, Hao Zhang, Hui Huang
Abstract: We introduce a novel representation for learning and generating Computer-Aided Design (CAD) models in the form of $\textit{boundary representations}$ (B-Reps). Our representation unifies the continuous geometric properties of B-Rep primitives in different orders (e.g., surfaces and curves) and their discrete topological relations in a $\textit{holistic latent}$ (HoLa) space. This is based on the simple observation that the topological connection between two surfaces is intrinsically tied to the geometry of their intersecting curve. Such a prior allows us to reformulate topology learning in B-Reps as a geometric reconstruction problem in Euclidean space. Specifically, we eliminate the presence of curves, vertices, and all the topological connections in the latent space by learning to distinguish and derive curve geometries from a pair of surface primitives via a neural intersection network. To this end, our holistic latent space is only defined on surfaces but encodes a full B-Rep model, including the geometry of surfaces, curves, vertices, and their topological relations. Our compact and holistic latent space facilitates the design of a first diffusion-based generator to take on a large variety of inputs including point clouds, single/multi-view images, 2D sketches, and text prompts. Our method significantly reduces ambiguities, redundancies, and incoherences among the generated B-Rep primitives, as well as training complexities inherent in prior multi-step B-Rep learning pipelines, while achieving greatly improved validity rate over current state of the art: 82% vs. $\approx$50%.