Processing math: 100%

CVPR.2025 - Highlight

| Total: 388

#1 TKG-DM: Training-free Chroma Key Content Generation Diffusion Model [PDF23] [Copy] [Kimi23] [REL]

Authors: Ryugo Morita, Stanislav Frolov, Brian Bernhard Moser, Takahiro Shirakawa, Ko Watanabe, Andreas Dengel, Jinjia Zhou

Diffusion models have enabled the generation of high-quality images with a strong focus on realism and textual fidelity. Yet, large-scale text-to-image models, such as Stable Diffusion, struggle to generate images where foreground objects are placed over a chroma key background, limiting their ability to separate foreground and background elements without fine-tuning. To address this limitation, we present a novel Training-Free Chroma Key Content Generation Diffusion Model (TKG-DM), which optimizes the initial random noise to produce images with foreground objects on a specifiable color background. Our proposed method is the first to explore the manipulation of the color aspects in initial noise for controlled background generation, enabling precise separation of foreground and background without fine-tuning. Extensive experiments demonstrate that our training-free method outperforms existing methods in both qualitative and quantitative evaluations, matching or surpassing fine-tuned models. Finally, we successfully extend it to other tasks (e.g., consistency models and text-to-video), highlighting its transformative potential across various generative applications where independent control of foreground and background is crucial.

Subject: CVPR.2025 - Highlight


#2 Context-Aware Multimodal Pretraining [PDF19] [Copy] [Kimi16] [REL]

Authors: Karsten Roth, Zeynep Akata, Dima Damen, Ivana Balazevic, Olivier J. Henaff

Large-scale multimodal representation learning successfully optimizes for zero-shot transfer at test time. Yet the standard pretraining paradigm (contrastive learning on large amounts of image-text data) does not explicitly encourage representations to support few-shot adaptation. In this work, we propose a simple, but carefully designed extension to multimodal pretraining which enables representations to accommodate additional context. Using this objective, we show that vision-language models can be trained to exhibit significantly increased few-shot adaptation: across 21 downstream tasks, we find up to four-fold improvements in test-time sample efficiency, and average few-shot adaptation gains of over 5\%, while retaining zero-shot generalization performance across model scales and training durations. In particular, equipped with simple, training-free, metric-based adaptation mechanisms, our representations surpass significantly more complex optimization-based adaptation schemes.

Subject: CVPR.2025 - Highlight


#3 Towards RAW Object Detection in Diverse Conditions [PDF13] [Copy] [Kimi6] [REL]

Authors: Zhong-Yu Li, Xin Jin, Bo-Yuan Sun, Chun-Le Guo, Ming-Ming Cheng

Existing object detection methods often consider sRGB input, which was compressed from RAW data using ISP originally designed for visualization. However, such compression might lose crucial information for detection, especially under complex light and weather conditions. We introduce the AODRaw dataset, which offers 7,785 high-resolution real RAW images with 135,601 annotated instances spanning 62 categories, capturing a broad range of indoor and outdoor scenes under 9 distinct light and weather conditions. Based on AODRaw that supports RAW and sRGB object detection, we provide a comprehensive benchmark for evaluating current detection methods. We find that sRGB pre-training constrains the potential of RAW object detection due to the domain gap between sRGB and RAW, prompting us to directly pre-train on the RAW domain. However, it is harder for RAW pre-training to learn rich representations than sRGB pre-training due to the camera noise. To assist RAW pre-training, we distill the knowledge from an off-the-shelf model pre-trained on the sRGB domain. As a result, we achieve substantial improvements under diverse and adverse conditions without relying on extra pre-processing modules. The code and dataset will be made publicly available.

Subject: CVPR.2025 - Highlight


#4 ImagineFSL: Self-Supervised Pretraining Matters on Imagined Base Set for VLM-based Few-shot Learning [PDF11] [Copy] [Kimi4] [REL]

Authors: Haoyuan Yang, Xiaoou Li, Jiaming Lv, Xianjun Cheng, Qilong Wang, Peihua Li

Adapting CLIP models for few-shot recognition has recently attracted significant attention. Despite considerable progress, these adaptations remain hindered by the pervasive challenge of data scarcity. Text-to-image models, capable of generating abundant photorealistic labeled images, offer a promising solution. However, existing approaches treat synthetic images merely as complements to real images, rather than as standalone knowledge repositories stemming from distinct foundation models. To overcome this limitation, we reconceptualize synthetic images as an *imagined base set*, i.e., a unique, large-scale synthetic dataset encompassing diverse concepts. We introduce a novel CLIP adaptation methodology called *ImagineFSL*, involving pretraining on the imagined base set followed by fine-tuning on downstream few-shot tasks. We find that, compared to no pretraining, both supervised and self-supervised pretraining are beneficial, with the latter providing better performance. Building on this finding, we propose an improved self-supervised method tailored for few-shot scenarios, enhancing the transferability of representations from synthetic to real image domains. Additionally, we present an image generation pipeline that employs chain-of-thought and in-context learning techniques, harnessing foundation models to automatically generate diverse, realistic images. Our methods are validated across eleven datasets, consistently outperforming state-of-the-art methods by substantial margins.

Subject: CVPR.2025 - Highlight


#5 Tuning the Frequencies: Robust Training for Sinusoidal Neural Networks [PDF6] [Copy] [Kimi4] [REL]

Authors: Tiago Novello, Diana Aldana, Andre Araujo, Luiz Velho

Sinusoidal neural networks have been shown effective as implicit neural representations (INRs) of low-dimensional signals, due to their smoothness and high representation capacity. However, initializing and training them remain empirical tasks which lack on deeper understanding to guide the learning process. To fill this gap, our work introduces a theoretical framework that explains the capacity property of sinusoidal networks and offers robust control mechanisms for initialization and training. Our analysis is based on a novel amplitude-phase expansion of the sinusoidal multilayer perceptron, showing how its layer compositions produce a large number of new frequencies expressed as integer combinations of the input frequencies. This relationship can be directly used to initialize the input neurons, as a form of spectral sampling, and to bound the network's spectrum while training. Our method, referred to as TUNER (TUNing sinusoidal nEtwoRks), greatly improves the stability and convergence of sinusoidal INR training, leading to detailed reconstructions, while preventing overfitting.

Subject: CVPR.2025 - Highlight


#6 Perceptually Accurate 3D Talking Head Generation: New Definitions, Speech-Mesh Representation, and Evaluation Metrics [PDF4] [Copy] [Kimi3] [REL]

Authors: Lee Chae-Yeon, Oh Hyun-Bin, Han EunGi, Kim Sung-Bin, Suekyeong Nam, Tae-Hyun Oh

Recent advancements in speech-driven 3D talking head generation have achieved impressive advance in lip synchronization. However, existing models still fall short in capturing a perceptual alignment between diverse speech characteristics and lip movements. In this work, we define essential criteria—temporal synchronization, lip readability, and expressiveness— for perceptually accurate lip movements in response to speech signals. We also introduce a speech-mesh synchronized representation that captures the intricate correspondence between speech and facial mesh. We plug in this representation as a perceptual loss to guide lip movements, ensuring they are perceptually aligned with the given speech. Additionally, we utilize this representation as a perceptual metric and introduce two other physically-grounded lip synchronization metrics to evaluate these three criteria. Experiments demonstrate that training 3D talking head models with our perceptual loss significantly enhances all three aspects of perceptually accurate lip synchronization. Codes will be released if accepted.

Subject: CVPR.2025 - Highlight


#7 Diffusion-based Realistic Listening Head Generation via Hybrid Motion Modeling [PDF6] [Copy] [Kimi5] [REL]

Authors: Yinuo Wang, Yanbo Fan, Xuan Wang, Guo Yu, Fei Wang

Listening head generation aims to synthesize non-verbal responsive listening head videos that naturally react to a certain speaker, for which, both realistic head movements, expressive facial expressions, and high visual qualities are expected. Previous approaches typically follow a two-stage pipeline that first generates intermediate 3D motion signals such as 3DMM coefficients, and then synthesizes the videos by deterministic rendering, suffering from limited motion expressiveness and low visual quality (eg, 256×256). In this work, we propose a novel listening head generation method that harnesses the generative capabilities of the diffusion model for both motion generation and high-quality rendering. Crucially, we propose an effective hybrid motion modeling module that addresses training difficulties caused by the scarcity of listening head data while preserving the intricate details that may be lost in explicit motion representations. We further develop a tailored control guidance for head pose and facial expression, by integrating their intrinsic motion characteristics. Our method enables high-fidelity video generation with 512×512 resolution and delivers vivid listener motion feedback. We conduct comprehensive experiments and obtain superior performance in terms of both visual quality and motion expressiveness compared to existing methods.

Subject: CVPR.2025 - Highlight


#8 Hyperbolic Safety-Aware Vision-Language Models [PDF8] [Copy] [Kimi8] [REL]

Authors: Tobia Poppi, Tejaswi Kasarla, Pascal Mettes, Lorenzo Baraldi, Rita Cucchiara

Addressing the retrieval of unsafe content from vision-language models such as CLIP is an important step towards real-world integration. Current efforts have relied on unlearning techniques that try to erase the model’s knowledge of unsafe concepts. While effective in reducing unwanted outputs, unlearning limits the model's capacity to discern between safe and unsafe content. In this work, we introduce a novel approach that shifts from unlearning to an awareness paradigm by leveraging the inherent hierarchical properties of the hyperbolic space. We propose to encode safe and unsafe content as an entailment hierarchy, where both are placed in different regions of hyperbolic space. Our HySAC, Hyperbolic Safety-Aware CLIP, employs entailment loss functions to model the hierarchical and asymmetrical relations between safe and unsafe image-text pairs. This modelling – ineffective in standard vision-language models due to their reliance on Euclidean embeddings – endows the model with awareness of unsafe content, enabling it to serve as both a multimodal unsafe classifier and a flexible content retriever, with the option to dynamically redirect unsafe queries toward safer alternatives or retain the original output. Extensive experiments show that our approach not only enhances safety recognition, but also establishes a more adaptable and interpretable framework for content moderation in vision-language models.

Subject: CVPR.2025 - Highlight


#9 XLRS-Bench: Could Your Multimodal LLMs Understand Extremely Large Ultra-High-Resolution Remote Sensing Imagery? [PDF5] [Copy] [Kimi5] [REL]

Authors: Fengxiang Wang, Hongzhen Wang, Zonghao Guo, Di Wang, Yulin Wang, Mingshuo Chen, Qiang Ma, Long Lan, Wenjing Yang, Jing Zhang, Zhiyuan Liu, Maosong Sun

The astonishing breakthrough of multimodal large language models (MLLMs) has necessitated new benchmarks to quantitatively assess their capabilities, reveal their limitations, and indicate future research directions. However, this is challenging in the context of remote sensing (RS), since the imagery features ultra-high resolution that incorporates extremely complex semantic relationships. Existing benchmarks usually adopt notably smaller image sizes than real-world RS scenarios, suffer from limited annotation quality, and consider insufficient dimensions of evaluation. To address these issues, we present XLRS-Bench: a comprehensive benchmark for evaluating the perception and reasoning capabilities of MLLMs in ultra-high-resolution RS scenarios. XLRS-Bench boasts the largest average image size (8500×8500) observed thus far, with all evaluation samples meticulously annotated manually, assisted by a novel semi-automatic captioner on ultra-high-resolution RS images. On top of the XLRS-Bench, 16 sub-tasks are defined to evaluate MLLMs' 6 kinds of perceptual abilities and 4 kinds of reasoning capabilities, with a primary emphasis on advanced cognitive processes that facilitate real-world decision-making and the capture of spatiotemporal changes. The results of both general and RS-focused MLLMs on XLRS-Bench indicate that further efforts are needed to enhance their performance in real RS scenarios. We will open source XLRS-Bench to support further research of developing more powerful MLLMs for RS.

Subject: CVPR.2025 - Highlight


#10 Improving Personalized Search with Regularized Low-Rank Parameter Updates [PDF7] [Copy] [Kimi3] [REL]

Authors: Fiona Ryan, Josef Sivic, Fabian Caba Heilbron, Judy Hoffman, James M. Rehg, Bryan Russell

Personalized vision-language retrieval seeks to recognize new concepts (e.g. "my dog Fido'') from only a few examples. This task is challenging because it requires not only learning a new concept from a few images, but also integrating the personal and general knowledge together to recognize the concept in different contexts. In this paper, we show how to effectively adapt the internal representation of a vision-language dual encoder model for personalized vision-language retrieval. We find that regularized low-rank adaption of a small set of parameters in the language encoder's final layer serves as a highly effective alternative to textual inversion for recognizing the personal concept while preserving general knowledge. Additionally, we explore strategies for combining parameters of multiple learned personal concepts, finding that parameter addition is effective. To evaluate how well general knowledge is preserved in a finetuned representation, we introduce a metric that measures image retrieval accuracy based on captions generated by a vision language model (VLM). Our approach achieves state-of-the-art accuracy on two benchmarks for personalized image retrieval with natural language queries -- DeepFashion2 and ConConChi -- outperforming the prior art by 4%-22% on personal retrievals.

Subject: CVPR.2025 - Highlight


#11 All-Optical Nonlinear Diffractive Deep Network for Ultrafast Image Denoising [PDF4] [Copy] [Kimi5] [REL]

Authors: Xiaoling Zhou, Zhemg Lee, Wei Ye, Rui Xie, Wenbo Zhang, Guanju Peng, Zongze Li, Shikun Zhang

Image denoising poses a significant challenge in image processing, aiming to remove noise and artifacts from input images. However, current denoising algorithms implemented on electronic chips frequently encounter latency issues and demand substantial computational resources. In this paper, we introduce an all-optical Nonlinear Diffractive Denoising Deep Network (N3DNet) for image denoising at the speed of light. Initially, we incorporate an image encoding and pre-denoising module into the Diffractive Deep Neural Network and integrate a nonlinear activation function, termed the phase exponential linear function, after each diffractive layer, thereby boosting the network's nonlinear modeling and denoising capabilities. Subsequently, we devise a new reinforcement learning algorithm called regularization-assisted deep Q-network to optimize N3DNet. Finally, leveraging 3D printing techniques, we fabricate N3DNet using the trained parameters and construct a physical experimental system for real-world applications. A new benchmark dataset, termed MIDD, is constructed for mode image denoising, comprising 120K pairs of noisy/noise-free images captured from real fiber communication systems across various transmission lengths. Through extensive simulation and real experiments, we validate that N3DNet outperforms both traditional and deep learning-based denoising approaches across various datasets. Remarkably, its processing speed is nearly 3,800 times faster than electronic chip-based methods.

Subject: CVPR.2025 - Highlight


#12 NTClick: Achieving Precise Interactive Segmentation With Noise-tolerant Clicks [PDF7] [Copy] [Kimi3] [REL]

Authors: Chenyi Zhang, Ting Liu, Xiaochao Qu, Luoqi Liu, Yao Zhao, Yunchao Wei

Interactive segmentation is a pivotal task in computer vision, focused on predicting precise masks with minimal user input. Although the click has recently become the most prevalent form of interaction due to its flexibility and efficiency, its advantages diminish as the complexity and details of target objects increase because it's time-consuming and user-unfriendly to precisely locate and click on narrow, fine regions. To tackle this problem, we propose NTClick, a powerful click-based interactive segmentation method capable of predicting accurate masks even with imprecise user clicks when dealing with intricate targets. We first introduce a novel interaction form called Noist-tolerant Click, a type of click that does not require user's precise localization when selecting fine regions. Then, we design a two-stage workflow, consisting of an Explicit Coarse Perception network for initial estimation and a High Resolution Refinement network for final classification. Quantitative results across extensive datasets demonstrate that NTClick not only maintains an efficient and flexible interaction mode but also significantly outperforms existing methods in segmentation accuracy.

Subject: CVPR.2025 - Highlight


#13 Balanced Rate-Distortion Optimization in Learned Image Compression [PDF1] [Copy] [Kimi2] [REL]

Authors: Yichi Zhang, Zhihao Duan, Yuning Huang, Fengqing Zhu

Learned image compression (LIC) using deep learning architectures has seen significant advancements, yet standard rate-distortion (R-D) optimization often encounters imbalanced updates due to diverse gradients of the rate and distortion objectives. This imbalance can lead to suboptimal optimization, where one objective dominates, thereby reducing overall compression efficiency. To address this challenge, we reformulate R-D optimization as a multi-objective optimization (MOO) problem and introduce two balanced R-D optimization strategies that adaptively adjust gradient updates to achieve more equitable improvements in both rate and distortion. The first proposed strategy utilizes a coarse-to-fine gradient descent approach along standard R-D optimization trajectories, making it particularly suitable for training LIC models from scratch. The second proposed strategy analytically addresses the reformulated optimization as a quadratic programming problem with an equality constraint, which is ideal for fine-tuning existing models. Experimental results demonstrate that both proposed methods enhance the R-D performance of LIC models, achieving around a 2\% BD-Rate reduction with acceptable additional training cost, leading to a more balanced and efficient optimization process. The code will be made publicly available.

Subject: CVPR.2025 - Highlight


#14 Estimating Body and Hand Motion in an Ego-sensed World [PDF4] [Copy] [Kimi2] [REL]

Authors: Brent Yi, Vickie Ye, Maya Zheng, Yunqi Li, Lea Müller, Georgios Pavlakos, Yi Ma, Jitendra Malik, Angjoo Kanazawa

We present EgoAllo, a system for human motion estimation from a head-mounted device. Using only egocentric SLAM poses and images, EgoAllo guides sampling from a conditional diffusion model to estimate 3D body pose, height, and hand parameters that capture a device wearer's actions in the allocentric coordinate frame of the scene. To achieve this, our key insight is in representation: we propose spatial and temporal invariance criteria for improving model performance, from which we derive a head motion conditioning parameterization that improves estimation by up to 18%. We also show how the bodies estimated by our system can improve hand estimation: the resulting kinematic and temporal constraints can reduce world-frame errors in single-frame estimates by 40%.

Subject: CVPR.2025 - Highlight


#15 Which Viewpoint Shows it Best? Language for Weakly Supervising View Selection in Multi-view Instructional Videos [PDF2] [Copy] [Kimi1] [REL]

Authors: Sagnik Majumder, Tushar Nagarajan, Ziad Al-Halah, Reina Pradhan, Kristen Grauman

Given a multi-view video, which viewpoint is most informative for a human observer? Existing methods rely on heuristics or expensive “best-view" supervision to answer this question, limiting their applicability. We propose a weakly supervised approach that leverages language accompanying an instructional multi-view video as a means to recover its most informative viewpoint(s). Our key hypothesis is that the more accurately an individual view can predict a view-agnostic text summary, the more informative it is. To put this into action, we propose a framework that uses the relative accuracy of view-dependent caption predictions as a proxy for best view pseudo-labels. Then, those pseudo-labels are used to train a view selector, together with an auxiliary camera pose predictor that enhances view-sensitivity. During inference, our model takes as input only a multi-view video—no language or camera poses—and returns the best viewpoint to watch at each timestep. On two challenging datasets comprised of diverse multi-camera setups and how-to activities, our model consistently outperforms state-of-the-art baselines, both with quantitative metrics and human evaluation.

Subject: CVPR.2025 - Highlight


#16 COUNTS: Benchmarking Object Detectors and Multimodal Large Language Models under Distribution Shifts [PDF5] [Copy] [Kimi2] [REL]

Authors: Jiansheng Li, Xingxuan Zhang, Hao Zou, Yige Guo, Renzhe Xu, Yilong Liu, Chuzhao Zhu, Yue He, Peng Cui

Current object detectors often suffer significant performance degradation in real-world applications when encountering distributional shifts, posing serious risks in high-stakes domains such as autonomous driving and medical diagnosis. Consequently, the out-of-distribution (OOD) generalization capability of object detectors has garnered increasing attention from researchers. Despite this growing interest, there remains a lack of a large-scale, comprehensive dataset and evaluation benchmark with fine-grained annotations tailored to assess the OOD generalization on more intricate tasks like object detection and grounding. To address this gap, we introduce COUNTS, a large-scale OOD dataset with object-level annotations. COUNTS encompasses 14 natural distributional shifts, over 222K samples, and more than 1,196K labeled bounding boxes. Leveraging COUNTS, we introduce two novel benchmarks: O(OD) and OODG. OODOD is designed to comprehensively evaluate the OOD generalization capabilities of object detectors by utilizing controlled distribution shifts between training and testing data. OODG, on the other hand, aims to assess the OOD generalization of grounding abilities in multimodal large language models (MLLMs). Our findings reveal that, while large models and extensive pre-training data substantially enhance performance in in-distribution (IID) scenarios, significant limitations and opportunities for improvement persist in OOD contexts for both object detectors and MLLMs. In visual grounding tasks, even the advanced GPT-4o and Gemini-1.5 only achieve 56.7% and 28.0% accuracy, respectively. We hope COUNTS facilitates advancements in the development and assessment of robust object detectors and MLLMs capable of maintaining high performance under distributional shifts.

Subject: CVPR.2025 - Highlight


#17 ESC: Erasing Space Concept for Knowledge Deletion [PDF3] [Copy] [Kimi1] [REL]

Authors: Tae-Young Lee, Sundong Park, Minwoo Jeon, Hyoseok Hwang, Gyeong-Moon Park

As concerns regarding privacy in deep learning continue to grow, individuals are increasingly apprehensive about the potential exploitation of their personal knowledge in trained models. Despite several research efforts to address this, they often fail to consider the real-world demand from users for complete knowledge erasure. Furthermore, our investigation reveals that existing methods have a risk of leaking personal knowledge through embedding features. To address these issues, we introduce a novel concept of Knowledge Deletion (KD), an advanced task that considers both concerns, and provides an appropriate metric, named Knowledge Retention score (KR), for assessing knowledge retention in feature space. To achieve this, we propose a novel training-free erasing approach named Erasing Space Concept (ESC), which restricts the important subspace for the forgetting knowledge by eliminating the relevant activations in the feature. In addition, we suggest ESC with Training (ESC-T), which uses a learnable mask to better balance the trade-off between forgetting and preserving knowledge in KD. Our extensive experiments on various datasets and models demonstrate that our proposed methods achieve the fastest and state-of-the-art performance. Notably, our methods are applicable to diverse forgetting scenarios, such as facial domain setting, demonstrating the generalizability of our methods.

Subject: CVPR.2025 - Highlight


#18 Scene-Centric Unsupervised Panoptic Segmentation [PDF5] [Copy] [Kimi2] [REL]

Authors: Oliver Hahn, Christoph Reich, Nikita Araslanov, Daniel Cremers, Christian Rupprecht, Stefan Roth

Unsupervised panoptic segmentation aims to partition an image into semantically meaningful regions and distinct object instances without training on manually annotated data. In contrast to prior work on unsupervised panoptic scene understanding, we eliminate the need for object-centric training data, enabling the unsupervised understanding of complex scenes. To that end, we present the first unsupervised panoptic method that directly trains on scene-centric imagery. In particular, we propose an approach to obtain high-resolution panoptic pseudo labels on complex scene-centric data combining visual representations, depth, and motion cues. Utilizing both pseudo-label training and a panoptic self-training strategy yields a novel approach that accurately predicts panoptic segmentation of complex scenes without requiring any human annotations. Our approach significantly improves panoptic quality, e.g., surpassing the recent state of the art in unsupervised panoptic segmentation on Cityscapes by 9.4% points in PQ.

Subject: CVPR.2025 - Highlight


#19 RGBAvatar: Reduced Gaussian Blendshapes for Online Modeling of Head Avatars [PDF2] [Copy] [Kimi2] [REL]

Authors: Linzhou Li, Yumeng Li, Yanlin Weng, Youyi Zheng, Kun Zhou

We present Reduced Gaussian Blendshapes Avatar (RGBAvatar), a method for reconstructing photorealistic, animatable head avatars at speeds sufficient for on-the-fly reconstruction. Unlike prior approaches that utilize linear bases from 3D morphable models (3DMM) to model Gaussian blendshapes, our method maps tracked 3DMM parameters into reduced blendshape weights with an MLP, leading to a compact set of blendshape bases. The learned compact base composition effectively captures essential facial details for specific individuals, and does not rely on the fixed base composition weights of 3DMM, leading to enhanced reconstruction quality and higher efficiency. To further expedite the reconstruction process, we develop a novel color initialization estimation method and a batch-parallel Gaussian rasterization process, achieving state-of-the-art quality with training throughput of about 630 images per second. Moreover, we propose a local-global sampling strategy that enables direct on-the-fly reconstruction, immediately reconstructing the model as video streams in real time while achieving quality comparable to offline settings.

Subject: CVPR.2025 - Highlight


#20 MITracker: Multi-View Integration for Visual Object Tracking [PDF2] [Copy] [Kimi1] [REL]

Authors: Mengjie Xu, Yitao Zhu, Haotian Jiang, Jiaming Li, Zhenrong Shen, Sheng Wang, Haolin Huang, Xinyu Wang, Han Zhang, Qing Yang, Qian Wang

Multi-view object tracking (MVOT) offers promising solutions to challenges such as occlusion and target loss, which are common in traditional single-view tracking. However, progress has been limited by the lack of comprehensive multi-view datasets and effective cross-view integration methods. To overcome these limitations, we compiled a Multi-View object Tracking (MVTrack) dataset of 234K high-quality annotated frames featuring 27 distinct objects across various scenes. In conjunction with this dataset, we introduce a novel MVOT method, Multi-View Integration Tracker (MITracker), to efficiently integrate multi-view object features and provide stable tracking outcomes. MITracker can track any object in video frames of arbitrary length from arbitrary viewpoints. The key advancements of our method over traditional single-view approaches come from two aspects: (1) MITracker transforms 2D image features into a 3D feature volume and compresses it into a bird’s eye view (BEV) plane, facilitating inter-view information fusion; (2) we propose an attention mechanism that leverages geometric information from fused 3D feature volume to refine the tracking results at each view. MITracker outperforms existing methods on the MVTrack and GMTD datasets, achieving state-of-the-art performance.

Subject: CVPR.2025 - Highlight


#21 You See it, You Got it: Learning 3D Creation on Pose-Free Videos at Scale [PDF2] [Copy] [Kimi] [REL]

Authors: Baorui Ma, Huachen Gao, Haoge Deng, Zhengxiong Luo, Tiejun Huang, Lulu Tang, Xinlong Wang

Recent 3D generation models typically rely on limited-scale 3D `gold-labels' or 2D diffusion priors for 3D content creation. However, their performance is upper-bounded by constrained 3D priors due to the lack of scalable learning paradigms. In this work, we present See3D, a visual-conditional multi-view diffusion model trained on large-scale Internet videos for open-world 3D creation. The model aims to Get 3D knowledge by solely Seeing the visual contents from the vast and rapidly growing video data --- You See it, You Got it. To achieve this, we first scale up the training data using a proposed data curation pipeline that automatically filters out multi-view inconsistencies and insufficient observations from source videos. This results in a high-quality, richly diverse, large-scale dataset of multi-view images, termed WebVi3D, containing 320M frames from 16M video clips. Nevertheless, learning generic 3D priors from videos without explicit 3D geometry or camera pose annotations is nontrivial, and annotating poses for web-scale videos is prohibitively expensive. To eliminate the need for pose conditions, we introduce an innovative visual-condition - a purely 2D-inductive visual signal generated by adding time-dependent noise to the masked video data. Finally, we introduce a novel visual-conditional 3D generation framework by integrating See3D into a warping-based pipeline for high-fidelity 3D generation. Our numerical and visual comparisons on single and sparse reconstruction benchmarks show that See3D, trained on cost-effective and scalable video data, achieves notable zero-shot and open-world generation capabilities, markedly outperforming models trained on costly and constrained 3D datasets. Additionally, our model naturally supports other image-conditioned 3D creation tasks, such as 3D editing, without further fine-tuning.

Subject: CVPR.2025 - Highlight


#22 InteractAnything: Zero-shot Human Object Interaction Synthesis via LLM Feedback and Object Affordance Parsing [PDF2] [Copy] [Kimi4] [REL]

Authors: Jinlu Zhang, Yixin Chen, Zan Wang, Jie Yang, Yizhou Wang, Siyuan Huang

Recent advances in 3D human-centric generation have made significant progress. However, existing methods still struggle with generating novel Human-Object Interactions (HOIs), particularly for open-set objects. We identify three main challenges of this task: precise human object relation reasoning, adaptive affordance parsing for unseen objects, and realistic human pose synthesis that aligns with the description and 3D object geometry. In this work, we propose a novel zero-shot 3D HOI generation framework, leveraging the knowledge from large-scale pretrained models without training from specific datasets. More specifically, we first generate an initial human pose by sampling multiple hypotheses through multi-view SDS based on the input text and object geometry. We then utilize a pre-trained 2D image diffusion model to parse unseen objects and extract contact points, avoiding the limitations imposed by existing 3D asset knowledge. Finally, we introduce a detailed optimization to generate fine-grained, precise and natural interaction, enforcing realistic 3D contact between the involved body parts, including hands in grasp, and 3D object. This is achieved by distilling relational feedback from LLMs to capture detailed human-object relations from the text inputs. Extensive experiments validate the effectiveness of our approach compared to prior work, particularly in terms of the fine-grained nature of interactions and the ability to handle open-set 3D objects.

Subject: CVPR.2025 - Highlight


#23 Towards Zero-Shot Anomaly Detection and Reasoning with Multimodal Large Language Models [PDF10] [Copy] [Kimi6] [REL]

Authors: Jiacong Xu, Shao-Yuan Lo, Bardia Safaei, Vishal M. Patel, Isht Dwivedi

Zero-Shot Anomaly Detection (ZSAD) is an emerging AD paradigm. Unlike the traditional unsupervised AD setting that requires a large number of normal samples to train a model, ZSAD is more practical for handling data-restricted real-world scenarios. Recently, Multimodal Large Language Models (MLLMs) have shown revolutionary reasoning capabilities in various vision tasks. However, the reasoning of image abnormalities remains underexplored due to the lack of corresponding datasets and benchmarks. To facilitate research in anomaly detection and reasoning, we establish the first visual instruction tuning dataset, Anomaly-Instruct-125k, and the evaluation benchmark, VisA-D&R. Through investigation with our benchmark, we reveal that current MLLMs like GPT-4o cannot accurately detect and describe fine-grained anomalous details in images. To address this, we propose Anomaly-OneVision (Anomaly-OV), the first specialist visual assistant for ZSAD and reasoning, based on LLaVA-OneVision. Inspired by human behavior in visual inspection, Anomaly-OV leverages a Look-Twice Feature Matching (LTFM) mechanism to adaptively select and emphasize abnormal visual tokens for its LLM. Extensive experiments demonstrate that Anomaly-OV achieves significant improvements over advanced generalist models in both detection and reasoning. Furthermore, extensions to medical and 3D anomaly reasoning are provided for future study.

Subject: CVPR.2025 - Highlight


#24 4Real-Video: Learning Generalizable Photo-Realistic 4D Video Diffusion [PDF3] [Copy] [Kimi1] [REL]

Authors: Chaoyang Wang, Peiye Zhuang, Tuan Duc Ngo, Willi Menapace, Aliaksandr Siarohin, Michael Vasilkovsky, Ivan Skorokhodov, Sergey Tulyakov, Peter Wonka, Hsin-Ying Lee

We propose 4Real-Video, a novel framework for generating 4D videos, organized as a grid of video frames with both time and viewpoint axes. In this grid, each row contains frames sharing the same timestep, while each column contains frames from the same viewpoint. One stream performs viewpoint updates on columns, and the other stream performs temporal updates on rows. After each diffusion transformer layer, a newly designed synchronization layer exchanges information between the two token streams. We propose two implementations of the synchronization layer, using either hard or soft synchronization.This feedforward architecture improves upon previous work in three ways: higher inference speed, enhanced visual quality (measured by FVD, CLIP, and VideoScore), and improved temporal and viewpoint consistency (measured by VideoScore, GIM-Confidence, and Dust3R-Confidence).

Subject: CVPR.2025 - Highlight


#25 ICP: Immediate Compensation Pruning for Mid-to-high Sparsity [PDF2] [Copy] [Kimi2] [REL]

Authors: Xin Luo, Xueming Fu, Zihang Jiang, S. Kevin Zhou

The increasing adoption of large-scale models under 7 billion parameters in both language and vision domains enables inference tasks on a single consumer-grade GPU but makes fine-tuning models of this scale, especially 7B models, challenging. This limits the applicability of pruning methods that require full fine-tuning. Meanwhile, pruning methods that do not require fine-tuning perform well at low sparsity levels (10%-50%) but struggle at mid-to-high sparsity levels (50%-70%), where the error behaves equivalently to that of semi-structured pruning. To address these issues, this paper introduces ICP, which finds a balance between full fine-tuning and zero fine-tuning. First, Sparsity Rearrange is used to reorganize the predefined sparsity levels, followed by Block-wise Compensate Pruning, which alternates pruning and compensation on the model’s backbone, fully utilizing inference results while avoiding full model fine-tuning. Experiments show that ICP improves performance at mid-to-high sparsity levels compared to baselines, with only a slight increase in pruning time and no additional peak memory overhead.

Subject: CVPR.2025 - Highlight