CVPR 2025 论文列表

Relative camera pose estimation between two images is a fundamental task in 3D computer vision. Recently, many relative pose estimation networks have been explored for learning a mapping from two input images to their corresponding relative pose, however, the estimated relative poses by these methods do not have the intrinsic Pose Permutation Equivariance (PPE) property: the estimated relative pose from Image A to Image B should be the inverse of that from Image B to Image A. It means that permuting the input order of two images would cause these methods to obtain inconsistent relative poses. To address this problem, we firstly introduce the concept of PPE mapping, which indicates such a mapping that captures the intrinsic PPE property of relative poses. Then by enforcing the aforementioned PPE property, we propose a general framework for relative pose estimation, called EquiPose, which could easily accommodate various relative pose estimation networks in literature as its baseline models. We further theoretically prove that the proposed EquiPose framework could guarantee that its obtained mapping is a PPE mapping. Given a pre-trained baseline model, the proposed EquiPose framework could improve its performance even without fine-tuning, and could further boost its performance with fine-tuning. Experimental results on four public datasets demonstrate that EquiPose could significantly improve the performances of various state-of-the-art models.

Estimating full-body motion using the tracking signals of head and hands from VR devices holds great potential for various applications. However, the sparsity and unique distribution of observations present a significant challenge, resulting in an ill-posed problem with multiple feasible solutions (i.e., hypotheses). This amplifies uncertainty and ambiguity in full-body motion estimation, especially for the lower-body joints. Therefore, we propose a new method, EnvPoser, that employs a two-stage framework to perform full-body motion estimation using sparse tracking signals and pre-scanned environment from VR devices. EnvPoser models the multi-hypothesis nature of human motion through an uncertainty-aware estimation module in the first stage. In the second stage, we refine these multi-hypothesis estimates by integrating semantic and geometric environmental constraints, ensuring that the final motion estimation aligns realistically with both the environmental context and physical interactions.Qualitative and quantitative experiments on two public datasets demonstrate that our method achieves state-of-the-art performance, highlighting significant improvements in human motion estimation within motion-environment interaction scenarios. Project page: https://xspc.github.io/EnvPoser/.

Reconstructing complex reflections in real-world scenes from 2D images is essential for achieving photorealistic novel view synthesis. Existing methods that utilize environment maps to model reflections from distant lighting often struggle with high-frequency reflection details and fail to account for near-field reflections. In this work, we introduce EnvGS, a novel approach that employs a set of Gaussian primitives as an explicit 3D representation for capturing reflections of environments. These environment Gaussian primitives are incorporated with base Gaussian primitives to model the appearance of the whole scene. To efficiently render these environment Gaussian primitives, we developed a ray-tracing-based renderer that leverages the GPU's RT core for fast rendering. This allows us to jointly optimize our model for high-quality reconstruction while maintaining real-time rendering speeds. Results from multiple real-world and synthetic datasets demonstrate that our method produces significantly more detailed reflections, achieving the best rendering quality in real-time novel view synthesis. The code is available at https://zju3dv.github.io/envgs.

High-quality open-source datasets are essential for advancing deep neural networks. However, the unauthorized commercial use of these datasets has raised significant concerns about copyright protection. One promising approach is backdoor watermark-based dataset ownership verification (BW-DOV), in which dataset protectors implant specific backdoors into illicit models through dataset watermarking, enabling the tracing of these models through abnormal prediction behaviors. Unfortunately, the targeted nature of these BW-DOV methods can be maliciously exploited, potentially leading to harmful side effects. While existing harmless methods attempt to mitigate these risks, watermarked datasets can still negatively affect prediction results, partially compromising dataset functionality. In this paper, we propose a more harmless backdoor watermark, called EntropyMark, which improves prediction confidence without altering the final prediction results. For this purpose, an entropy-based constraint is introduced to regulate the probability distribution. Specifically, we design an iterative clean-label dataset watermarking framework. Our framework employs gradient matching and adaptive data selection to optimize backdoor injection. In parallel, we introduce a hypothesis test method grounded in entropy inconsistency to verify dataset ownership. Extensive experiments on benchmark datasets demonstrate the effectiveness, transferability, and defense resistance of our approach.

Automatically tracking and segmenting every video entity remains a significant challenge. Despite rapid advancements in video segmentation, even state-of-the-art models like SAM 2 struggle to consistently track all entities across a video--a task we refer to as Video Entity Segmentation.We propose EntitySAM, a framework for zero-shot video entity segmentation. EntitySAM extends SAM 2 by removing the need for explicit prompts, allowing automatic discovery and tracking of all entities, including those appearing in later frames. We incorporate query-based entity discovery and association into SAM 2, inspired by transformer-based object detectors. Specifically, we introduce an entity decoder to facilitate inter-object communication and an automatic prompt generator using learnable object queries. Additionally, we add a semantic encoder to enhance SAM 2's semantic awareness, improving segmentation quality. Trained on image-level mask annotations without category information from the COCO dataset, EntitySAM demonstrates strong generalization on four zero-shot video segmentation tasks: Video Entity, Panoptic, Instance, and Semantic Segmentation. Results on six popular benchmarks show that EntitySAM outperforms previous unified video segmentation methods and strong baselines, setting new standards for zero-shot video segmentation.

This paper presents EntityErasure, a novel diffusion-based inpainting method that can effectively erase entities without inducing unwanted sundries. To this end, we propose to address this problem by dividing it into amodal entity segmentation and completion, such that the region to inpaint takes only entities in the non-inpainting area as reference, avoiding the possibility to generate unpredictable sundries. Moreover, we develop two entity segmentation based metrics for quantitatively assessing the performance of object erasure, which are shown be more effective than existing metrics. Experimental results demonstrate that our approach outperforms other state-of-the-art object erasure methods. Our code and data are available at https://zyxunh.github.io/EntityErasure-ProjectPage/.

This paper presents a novel pipeline named EnliveningGS, which enables active locomotion of 3D models represented with 3D Gaussian splatting (3DGS). We are inspired by the fact that real-world lives pose their bodies in a natural and physically meaningful manner by compressing or elongating muscle fibers embedded in the body. EnliveningGS aims to replicate the similar functionality of 3DGS models so that the object within a 3DGS scene acts like a living creature rather than a static shape --- they walk, jump, and twist in the scene under provided motion trajectories driven by muscle activations. While the concept is straightforward, many challenging technical difficulties need to be taken care of. Synthesizing realistic locomotion of a 3DGS model embodies an inverse physics problem of very high dimensions. The core challenge is how to efficiently and robustly model frictional contacts between an "enlivened model" and the environment, as it is the composition of contact/collision/friction forces triggered by muscle activation that generates the final movement of the object. We propose a hybrid numerical method mixing LCP and penalty method to tackle this NP-hard problem robustly. Our pipeline also addresses the limitation of existing 3DGS deformation algorithms and inpainting the missing information when models move around.

Paired image-text data with subtle variations in-between (e.g., people holding surfboards vs. people holding shovels) hold the promise of producing Vision-Language Models with proper compositional understanding. Synthesizing such training data from generative models is a highly coveted prize due to the reduced cost of data collection. However, synthesizing training images for compositional learning presents three challenges: (1) efficiency in generating large quantities of images, (2) text alignment between the generated image and the caption in the exact place of the subtle change, and (3) image fidelity in ensuring sufficient similarity with the original real images in all other places. We propose SPARCL (Synthetic Perturbations for Advancing Robust Compositional Learning), which integrates image feature injection into a fast text-to-image generative model, followed by an image style transfer step, to meet the three challenges. Further, to cope with any residual issues of text alignment, we propose an adaptive margin loss to filter out potentially incorrect synthetic samples and focus the learning on informative hard samples. Evaluation on four compositional understanding benchmarks demonstrates that SPARCL significantly improves the compositionality of CLIP, boosting the average accuracy of the CLIP base model by over 8% across all benchmarks and outperforming state-of-the-art methods by 2% on three benchmarks.

Given an isolated garment image in a canonical product view and a separate image of a person, the virtual try-on task aims to generate a new image of the person wearing the target garment.Prior virtual try-on works face two major challenges in achieving this goal: a) the paired (human, garment) training data has limited availability; b) generating textures on the human that perfectly match that of the prompted garment is difficult, often resulting in distorted text and faded textures. Our work explores ways to tackle these issues through both synthetic data as well as model refinement. We introduce a garment extraction model that generates (human, synthetic garment) pairs from a single image of a clothed individual. The synthetic pairs can then be used to augment the training of virtual try-on. We also propose an Error-Aware Refinement-based Schrodinger Bridge (EARSB) that surgically targets localized generation errors for correcting the output of a base virtual try-on model. To identify likely errors, we propose a weakly-supervised error classifier that localizes regions for refinement, subsequently augmenting the Schrodinger Bridge's noise schedule with its confidence heatmap. Experiments on VITON-HD and DressCode-Upper demonstrate that our synthetic data augmentation enhances the performance of prior work, while EARSB improves the overall image quality. In user studies, our model is preferred by the users in an average of 59% of cases.

This paper tackles the problem of video question answering (VideoQA), a task that often requires multi-step reasoning and a profound understanding of spatial-temporal dynamics. While large video-language models perform well on benchmarks, they often lack explainability and spatial-temporal grounding. In this paper, we propose **A**gent-**o**f-**T**houghts **D**istillation (**AoTD**), a method that enhances models by incorporating automatically generated Chain-of-Thoughts (CoTs) into the instruction-tuning process. Specifically, we leverage an agent-based system to decompose complex questions into sub-tasks, and address them with specialized vision models, the intermediate results are then treated as reasoning chains. We also introduce a verification mechanism using a large language model (LLM) to ensure the reliability of generated CoTs. Extensive experiments demonstrate that AoTD improves the performance on multiple-choice and open-ended benchmarks.

Trusted multi-view classification (TMVC) addresses variations in data quality by evaluating the reliability of each view based on prediction uncertainty at the evidence level, reducing the impact of low-quality views commonly encountered in real-world scenarios. However, existing TMVC methods often struggle to maintain robustness during testing, particularly when integrating noisy or corrupted views. This limitation arises because the evidence collected by TMVC may be unreliable, frequently providing incorrect information due to complex view distributions and optimization challenges, ultimately leading to classification performance degradation. To enhance the robustness of TMVC methods in real-world conditions, we propose a generalized evidence filtering mechanism that is compatible with various fusion strategies commonly used in TMVC, including Belief Constraint Fusion, Aleatory Cumulative Belief Fusion, and Averaging Belief Fusion. Specifically, we frame the identification of unreliable evidence as a multiple testing problem and introduce p-values to control the risk of false identification. By selectively down-weighting unreliable evidence during testing, our mechanism ensures robust fusion and mitigates performance degradation. Both theoretical guarantees and empirical results demonstrate significant improvements in the classification performance of TMVC methods, supporting their reliable application in challenging, real-world environments.

Foundational models such as the Segment Anything Model (SAM) are gaining traction in medical imaging segmentation, supporting multiple downstream tasks. However, such models are supervised in nature, still relying on large annotated datasets or prompts supplied by experts. Conventional techniques such as active learning to alleviate such limitations are limited in scope and still necessitate continuous human involvement and complex domain knowledge for label refinement or establishing reward ground truth. To address these challenges, we propose an enhanced Segment Anything Model (SAM) framework that utilizes annotation-efficient prompts generated in a fully unsupervised fashion, while still capturing essential semantic, location, and shape information through contrastive language-image pretraining and visual question answering. We adopt the direct preference optimization technique to design an optimal policy that enables the model to generate high-fidelity segmentations with simple ratings or rankings provided by a virtual annotator simulating the human annotation process. State-of-the-art performance of our framework in tasks such as lung segmentation, breast tumor segmentation, and organ segmentation across various modalities, including X-ray, ultrasound, and abdominal CT, justifies its effectiveness in low-annotation data scenarios.

Text-to-image diffusion models have demonstrated remarkable capabilities in creating images highly aligned with user prompts, yet their proclivity for memorizing training set images has sparked concerns about the originality of the generated images and privacy issues, potentially leading to legal complications for both model owners and users, particularly when the memorized images contain proprietary content. Although methods to mitigate these issues have been suggested, enhancing privacy often results in a significant decrease in the utility of the outputs, as indicated by text-alignment scores. To bridge the research gap, we introduce a novel method, PRSS, which refines the classifier-free guidance approach in diffusion models by integrating prompt re-anchoring (PR) to improve privacy and incorporating semantic prompt search (SS) to enhance utility. Extensive experiments across various privacy levels demonstrate that our approach consistently improves the privacy-utility trade-off, establishing a new state-of-the-art.

Online continual learning (OCL) seeks to learn new tasks from data streams that appear only once, while retaining knowledge of previously learned tasks. Most existing methods rely on replay, focusing on enhancing memory retention through regularization or distillation. However, they often overlook the adaptability of the model, limiting the ability to learn generalizable and discriminative features incrementally from online training data.To address this, we introduce a plug-and-play module, S6MOD, which can be integrated into most existing methods and directly improve adaptability. Specifically, S6MOD introduces an extra branch after the backbone, where a mixture of discretization selectively adjusts parameters in a selective state space model, enriching selective scan patterns such that the model can adaptively select the most sensitive discretization method for current dynamics.We further design a class-conditional routing algorithm for dynamic, uncertainty-based adjustment and implement a contrastive discretization loss to optimize it. Extensive experiments combining our module with various models demonstrate that S6MOD significantly enhances model adaptability, leading to substantial performance gains and achieving the state-of-the-art results. The code is available at https://github.com/MyToumaKazusa/S6MOD.

Few-shot Class-Incremental Learning (FSCIL) challenges models to adapt to new classes with limited samples, presenting greater difficulties than traditional classincremental learning. While existing approaches rely heavily on visual models and require additional training during base or incremental phases, we propose a training-free framework that leverages pre-trained visual-language models like CLIP. At the core of our approach is a novel Bilevel Modality Calibration (BiMC) strategy. Our framework initially performs intra-modal calibration, combining LLM-generated fine-grained category descriptions with visual prototypes from the base session to achieve precise classifier estimation. This is further complemented by inter-modal calibration that fuses pre-trained linguistic knowledge with task-specific visual priors to mitigate modality-specific biases. To enhance prediction robustness, we introduce additional metrics and strategies that maximize the utilization of limited data. Extensive experimental results demonstrate that our approach significantly outperforms existing methods. Code is available at: https://github.com/yychen016/BiMC.

The rapid growth of social media has led to the widespread sharing of individual portrait images, which pose serious privacy risks due to the capabilities of automatic face recognition (AFR) systems for mass surveillance. Hence, protecting facial privacy against unauthorized AFR systems is essential. Inspired by the generation capability of the emerging diffusion models, recent methods employ diffusion models to generate adversarial face images for privacy protection. However, they suffer from the diffusion purification effect, leading to a low protection success rate (PSR). In this paper, we first propose learning unconditional embeddings to increase the learning capacity for adversarial modifications and then use them to guide the modification of the adversarial latent code to weaken the diffusion purification effect. Moreover, we integrate an identity-preserving structure to maintain structural consistency between the original and generated images, allowing human observers to recognize the generated image as having the same identity as the original. Extensive experiments conducted on two public datasets, i.e., CelebA-HQ and LADN, demonstrate the superiority of our approach. The protected faces generated by our method outperform those produced by existing facial privacy protection approaches in terms of transferability and natural appearance. The code is available at https://github.com/parham1998/Facial-Privacy-Protection

Model quantization is an effective way to compress deep neural networks and accelerate the inference time on edge devices. Existing quantization methods usually require original data for calibration during the compressing process, which may be inaccessible due to privacy issues. A common way is to generate calibration data to mimic the origin data. However, the generators in these methods have the mode collapse problem, making them unable to synthesize diverse data. To solve this problem, we leverage the information from the full-precision model and enhance both inter-class and intra-class diversity for generating better calibration data, by devising a multi-layer features mixer and normalization flow based attention. Besides, novel regulation losses are proposed to make the generator produce diverse data with more patterns from the perspective of activated feature values and for the quantized model to learn better clip ranges adaptive to our diverse calibration data. Extensive experiments show that our method achieves state-of-the-art quantization results for both Transformer and CNN architectures. In addition, we visualize the generated data to verify that our strategies can effectively handle the mode collapse issue. Our codes are available at https://anonymous.4open.science/r/DFQ-84E6 and will be publicly available.

Dataset distillation has gained popularity as a technique for compressing large datasets into smaller, more efficient representations while retaining essential information for model training. Data features can be broadly divided into two types: instance-specific features, which capture unique, fine-grained details of individual examples, and class-general features, which represent shared, broad patterns across a class. However, previous approaches often struggle to balance these; some focus solely on class-general features, missing finer instance details, while others concentrate on instance-specific features, overlooking the shared characteristics essential for class-level understanding. In this paper, we propose the Non-Critical Region Refinement Dataset Distillation (NRR-DD) method, which preserves the instance-specific and fine-grained regions in synthetic data while enriching non-critical regions with more class-general information. This approach enables our models to leverage all pixel information to capture both types of features, thereby improving overall performance. Furthermore, we introduce Distance-Based Representative (DBR) knowledge transfer, which eliminates the need for soft labels in training by relying solely on the distance between synthetic data predictions and one-hot encoded labels. Experimental results demonstrate that our NRR-DD achieves state-of-the-art performance on both small-scale and large-scale datasets. Additionally, by storing only two distances per instance, our method achieves comparable results across various settings. Code will be available at https://github.com/tmtuan1307/NRR-DD.