CVPR 2025 Papers

Achieving realistic animated human avatars requires accurate modeling of pose-dependent clothing deformations. Existing learning-based methods heavily rely on the Linear Blend Skinning (LBS) of minimally-clothed human models like SMPL to model deformation. However, they struggle to handle loose clothing, such as long dresses, where the canonicalization process becomes ill-defined when the clothing is far from the body, leading to disjointed and fragmented results. To overcome this limitation, we propose FreeCloth, a novel hybrid framework to model challenging clothed humans. Our core idea is to use dedicated strategies to model different regions, depending on whether they are close to or distant from the body. Specifically, we segment the human body into three categories: unclothed, deformed, and generated. We simply replicate unclothed regions that require no deformation. For deformed regions close to the body, we leverage LBS to handle the deformation. As for the generated regions, which correspond to loose clothing areas, we introduce a novel free-form, part-aware generator to model them, as they are less affected by movements. This free-form generation paradigm brings enhanced flexibility and expressiveness to our hybrid framework, enabling it to capture the intricate geometric details of challenging loose clothing, such as skirts and dresses. Experimental results on the benchmark dataset featuring loose clothing demonstrate that FreeCloth achieves state-of-the-art performance with superior visual fidelity and realism, particularly in the most challenging cases.

Neural rendering has demonstrated remarkable success in high-quality 3D neural reconstruction and novel view synthesis with dense input views and accurate poses. However, applying it to sparse, unposed views in unbounded 360* scenes remains a challenging problem. In this paper, we propose a novel neural rendering framework to accomplish the unposed and extremely sparse-view 3D reconstruction in unbounded 360* scenes. To resolve the spatial ambiguity inherent in unbounded scenes with sparse input views, we propose a layered Gaussian-based representation to effectively model the scene with distinct spatial layers. By employing a dense stereo reconstruction model to recover coarse geometry, we introduce a layer-specific bootstrap optimization to refine the noise and fill occluded regions in the reconstruction. Furthermore, we propose an iterative fusion of reconstruction and generation alongside an uncertainty-aware training approach to facilitate mutual conditioning and enhancement between these two processes. Comprehensive experiments show that our approach outperforms existing state-of-the-art methods in terms of rendering quality and surface reconstruction accuracy. Project page: https://zju3dv.github.io/free360/

Diffusion-based human animation aims to animate a human character based on a source human image as well as driving signals such as a sequence of poses. Leveraging the generative capacity of diffusion model, existing approaches are able to generate high-fidelity poses, but struggle with significant viewpoint changes, especially in zoom-in/zoom-out scenarios where camera-character distance varies. This limits the applications such as cinematic shot type plan or camera control. We propose a pose-correlated reference selection diffusion network, supporting substantial viewpoint variations in human animation. Our key idea is to enable the network to utilize multiple reference images as input, since significant viewpoint changes often lead to missing appearance details on the human body. To eliminate the computational cost, we first introduce a novel pose correlation module to compute similarities between non-aligned target and source poses, and then propose an adaptive reference selection strategy, utilizing the attention map to identify key regions for animation generation. To train our model, we curated a large dataset from public TED talks featuring varied shots of the same character, helping the model learn synthesis for different perspectives. Our experimental results show that with the same number of reference images, our model performs favorably compared to the current SOTA methods under large viewpoint change. We further show that the adaptive reference selection is able to choose the most relevant reference regions to generate humans under free viewpoints.

Vision-Language Models (VLMs) have become prominent in open-world image recognition for their strong generalization abilities. Yet, their effectiveness in practical applications is compromised by domain shifts and distributional changes, especially when test data distributions diverge from training data. Therefore, the paradigm of test-time adaptation (TTA) has emerged, enabling the use of online off-the-shelf data at test time, supporting independent sample predictions, and eliminating reliance on test annotations. Traditional TTA methods, however, often rely on costly training or optimization processes, or make unrealistic assumptions about accessing or storing historical training and test data.Instead, this study proposes FreeTTA, a training-free and universally available method that makes no assumptions, to enhance the flexibility of TTA. More importantly, FreeTTA is the first to explicitly model the test data distribution, enabling the use of intrinsic relationships among test samples to enhance predictions of individual samples without simultaneous access--a direction not previously explored. FreeTTA achieves these advantages by introducing an online EM algorithm that utilizes zero-shot predictions from VLMs as priors to iteratively compute the posterior probabilities of each online test sample and update parameters. Experiments demonstrate that FreeTTA achieves stable and significant improvements compared to state-of-the-art methods across 15 datasets in both cross-domain and out-of-distribution settings.

This paper addresses multi-modal crowd counting with a novel `free lunch' training enhancement strategy that requires no additional data, parameters, or increased inference complexity. First, we introduce a cross-modal alignment technique as a plug-in post-processing step for the pre-trained backbone network, enhancing the model's ability to capture shared information across modalities. Second, we incorporate a regional density supervision mechanism during the fine-tuning stage, which differentiates features in regions with varying crowd densities. Extensive experiments on three multi-modal crowd counting datasets validate our approach, making it the first to achieve an MAE below 10 on RGBT-CC. The code is available at https://github.com/HenryCilence/Free-Lunch-Multimodal-Counting.

Real-world datasets follow an imbalanced distribution, which poses significant challenges in rare-category object detection. Recent studies tackle this problem by developing re-weighting and re-sampling methods, that utilise the class frequencies of the dataset. However, these techniques focus solely on the frequency statistics and ignore the distribution of the classes in image space, missing important information. In contrast to them, we propose Fractal CALibration (FRACAL): a novel post-calibration method for long-tailed object detection. FRACAL devises a logit adjustment method that utilises the fractal dimension to estimate how uniformly classes are distributed in image space. During inference, it uses the fractal dimension to inversely downweight the probabilities of uniformly spaced class predictions achieving balance in two axes: between frequent and rare categories, and between uniformly spaced and sparsely spaced classes. FRACAL is a post-processing method and it does not require any training, also it can be combined with many off-the-shelf models such as one-stage sigmoid detectors and two-stage instance segmentation models. FRACAL boosts the rare class performance by up to 8.6% and surpasses all previous methods on LVIS dataset, while showing good generalisation to other datasets such as COCO, V3Det and OpenImages. We provide the code in the Appendix.

Instance segmentation is essential for augmented reality and virtual reality (AR/VR) as it enables precise object recognition and interaction, enhancing the integration of virtual and real-world elements for an immersive experience. However, the high computational overhead of segmentation limits its application on resource-constrained AR/VR devices, causing large processing latency and degrading user experience. In contrast to conventional scenarios, AR/VR users typically focus on only a few regions within their field of view before shifting perspective, allowing segmentation to be concentrated on gaze-specific areas. This insight drives the need for efficient segmentation methods that prioritize processing instance of interest, reducing computational load and enhancing real-time performance. In this paper, we present a foveated instance segmentation(FovealSeg) framework that leverages real-time user gaze data to perform instance segmentation exclusively on instance of interest, resulting in substantial computational savings. Evaluation results show that FSNet achieves an IoU of 0.56 on ADE20K and 0.54 on LVIS, notably outperforming the baseline. The code is available at https://github.com/SAI-Lab-NYU/Foveated-Instance-Segmentation.

Ranking entities such as algorithms, devices, methods, or models based on their performances, while accounting for application-specific preferences, is a challenge. To address this challenge, we establish the foundations of a universal theory for performance-based ranking. First, we introduce a rigorous framework built on top of both the probability and order theories. Our new framework encompasses the elements necessary to (1) manipulate performances as mathematical objects, (2) express which performances are worse than or equivalent to others, (3) model tasks through a variable called satisfaction, (4) consider properties of the evaluation, (5) define scores, and (6) specify application-specific preferences through a variable called importance. On top of this framework, we propose the first axiomatic definition of performance orderings and performance-based rankings. Then, we introduce a universal parametric family of scores, called ranking scores, that can be used to establish rankings satisfying our axioms, while considering application-specific preferences. Finally, we show, in the case of two-class classification, that the family of ranking scores encompasses well-known performance scores, including the accuracy, the true positive rate (recall, sensitivity), the true negative rate (specificity), the positive predictive value (precision), and F1. However, we also show that some other scores commonly used to compare classifiers are unsuitable to derive performance orderings satisfying the axioms.

Tremendous progress has been made in deep stereo matching to excel on benchmark datasets through per-domain fine-tuning. However, achieving strong zero-shot generalization - a hallmark of foundation models in other computer vision tasks - remains challenging for stereo matching. We introduce FoundationStereo, a foundation model for stereo depth estimation designed to achieve strong zero shot generalization. To this end, we first construct a large scale (1M stereo pairs) synthetic training dataset featuring large diversity and high photorealism, followed by an automatic self-curation pipeline to remove ambiguous samples. We then design a number of network architecture components to enhance scalability, including a side-tuning feature backbone that adapts rich monocular priors from vision foundation models to mitigate the sim-to-real gap, and long-range context reasoning for effective cost volume filtering. Together, these components lead to strong robustness and accuracy across domains, establishing a new standard in zero-shot stereo depth estimation. Project page: https://nvlabs.github.io/FoundationStereo

Despite remarkable progress in image generation models, generating realistic hands remains a persistent challenge due to their complex articulation, varying viewpoints, and frequent occlusions. We present FoundHand, a large-scale domain-specific diffusion model for synthesizing single and dual hand images. To train our model, we introduce FoundHand-10M, a large-scale hand dataset with 2D keypoints and segmentation mask annotations. Our insight is to use 2D hand keypoints as a universal representation that encodes both hand articulation and camera viewpoint. FoundHand learns from image pairs to capture physically plausible hand articulations, natively enables precise control through 2D keypoints, and supports appearance control. Our model exhibits core capabilities that include the ability to repose hands, transfer hand appearance, and even synthesize novel views. This leads to zero-shot capabilities for fixing malformed hands in previously generated images, or synthesizing hand video sequences. We present extensive experiments and evaluations that demonstrate state-of-the-art performance of our method.

Ensuring auditability and verifiability in FL is both challenging and essential to guarantee that local data remains untampered and client updates are trustworthy. Recent FL frameworks assess client contributions through a trusted central server using various client selection and aggregation techniques. However, reliance on a central server can create a single point of failure, making it vulnerable to privacy-centric attacks and limiting its ability to audit and verify client-side data contributions due to restricted access. In addition, data quality and fairness evaluations are often inadequate, failing to distinguish between high-impact contributions and those from low-quality or poisoned data. To address these challenges, we propose Federated Auditable and Verifiable Data valuation (FAVD), a privacy-preserving method that ensures auditability and verifiability of client contributions through data valuation, independent of any central authority or predefined training algorithm. FAVD utilizes shared local data density functions to construct a global density function, aligning data contributions and facilitating effective valuation prior to local model training. This proactive approach improves transparency in data valuation and ensures that only benign updates are generated, even in the presence of malicious data. Further, to mitigate privacy risks associated with sharing data density functions, we add Gaussian noise to each client's local density function before sharing it with the server. We theoretically demonstrate the convergence, auditability, and verifiability of FAVD, along with its resilience against data poisoning threats. Our experiments on five diverse benchmarks, including three medical datasets, show that FAVD achieves significant performance gains, accurate data valuation, and fair client contributions under threat, highlighting its reliability as a trustworthy FL approach.

Learning from label proportions (LLP), i.e. a challenging weakly-supervised learning task, aims to train a classifier by using bags of instances and the proportions of classes within bags, rather than annotated labels for each instance. Beyond the traditional bag-level loss, the mainstream methodology of LLP is to incorporate an auxiliary instance-level loss with pseudo-labels formed by predictions. Unfortunately, we empirically observed that the pseudo-labels are often inaccurate and even meaningless, especially for the scenarios with large bag sizes, hurting the classifier induction. To alleviate this problem, we suggest a novel LLP method, namely Learning Label Proportions with Auxiliary High-confident Instance-level Loss (L^2P-AHIL). Specifically, we propose a dual entropy-based weight (DEW) method to adaptively measure the confidences of pseudo-labels. It simultaneously emphasizes accurate predictions at the bag level and avoids smoothing predictions, which tend to be meaningless. We then form high-confident instance-level loss with DEW, and jointly optimize it with the bag-level loss in a self-training manner. The experimental results on benchmark datasets show that L^2P-AHIL can surpass the existing baseline methods, and the performance gain can be more significant as the bag size increases. The implementation of our method is available at https://github.com/TianhaoMa5/LLP-AHIL.

Place recognition is essential to maintain global consistency in large-scale localization systems. While research in urban environments has progressed significantly using LiDARs or cameras, applications in natural forest-like environments remain largely underexplored. Furthermore, forests present particular challenges due to high self-similarity and substantial variations in vegetation growth over time. In this work, we propose a robust LiDAR-based place recognition method for natural forests, ForestLPR. We hypothesize that a set of cross-sectional images of the forest's geometry at different heights contains the information needed to recognize revisiting a place. The cross-sectional images are represented by bird's-eye view (BEV) density images of horizontal slices of the point cloud at different heights. Our approach utilizes a visual transformer as the shared backbone to produce sets of local descriptors and introduces a multi-BEV interaction module to attend to information at different heights adaptively. It is followed by an aggregation layer that produces a rotation-invariant place descriptor. We evaluated the efficacy of our method extensively on real-world data from public benchmarks as well as robotic datasets and compared it against the state-of-the-art (SOTA) methods. The results indicate that ForestLPR has consistently good performance on all evaluations and achieves an average increase of 7.38% and 9.11% on Recall@1 over the closest competitor on intra-sequence loop closure detection and inter-sequence re-localization, respectively, validating our hypothesis.

Recently, the rapid development of AIGC has significantly boosted the diversities of fake media spread in the Internet, posing unprecedented threats to social security, politics, law, and etc.To detect the ever-increasingly **diverse** malicious fake media in the new era of AIGC, recent studies have proposed to exploit Large Vision Language Models (LVLMs) to design **robust** forgery detectors due to their impressive performance on a **wide** range of multimodal tasks.However, it still lacks a comprehensive benchmark designed to comprehensively assess LVLMs' discerning capabilities on forgery media.To fill this gap, we present Forensics-Bench, a new forgery detection evaluation benchmark suite to assess LVLMs across massive forgery detection tasks, requiring comprehensive recognition, location and reasoning capabilities on diverse forgeries.Forensics-Bench comprises 63,292 meticulously curated multi-choicevisual questions, covering 112 unique forgery detection types from 5 perspectives: forgery semantics, forgery modalities, forgery tasks, forgery types and forgery models.We conduct thorough evaluations on 22 open-sourced LVLMs and 3 proprietary models GPT-4o, Gemini 1.5 Pro, and Claude 3.5 Sonnet, highlighting the significant challenges of comprehensive forgery detection posed by Forensics-Bench.We anticipate that Forensics-Bench will motivate the community to advance the frontier of LVLMs, striving for all-around forgery detectors in the era of AIGC.

We describe the Forensics Adapter, an adapter network designed to transform CLIP into an effective and generalizable face forgery detector. Although CLIP is highly versatile, adapting it for face forgery detection is non-trivial as forgery-related knowledge is entangled with a wide range of unrelated knowledge. Existing methods treat CLIP merely as a feature extractor, lacking task-specific adaptation, which limits their effectiveness. To address this, we introduce an adapter to learn face forgery traces -- the blending boundaries unique to forged faces, guided by task-specific objectives. Then we enhance the CLIP visual tokens with a dedicated interaction strategy that communicates knowledge across CLIP and the adapter. Since the adapter is alongside CLIP, its versatility is highly retained, naturally ensuring strong generalizability in face forgery detection. With only 5.7M trainable parameters, our method achieves a significant performance boost, improving by approximately 7% on average across five standard datasets. We believe the proposed method can serve as a baseline for future CLIP-based face forgery detection methods.

The emergence of advanced AI-based tools to generate realistic images poses significant challenges for forensic detection and source attribution, especially as new generative techniques appear rapidly. Traditional methods often fail to generalize to unseen generators due to reliance on features specific to known sources during training. To address this problem, we propose a novel approach that explicitly models forensic microstructures--subtle, pixel-level patterns unique to the image creation process. Using only real images in a self-supervised manner, we learn a set of diverse predictive filters to extract residuals that capture different aspects of these microstructures. By jointly modeling these residuals across multiple scales, we obtain a compact model whose parameters constitute a unique forensic self-description for each image. This self-description enables us to perform zero-shot detection of synthetic images, open-set source attribution of images, and clustering based on source without prior knowledge. Extensive experiments demonstrate that our method achieves superior accuracy and adaptability compared to competing techniques, advancing the state of the art in synthetic media forensics.

The rapid development of generative models has significantly advanced font generation. However, limited exploration has been devoted to the evaluation and interpretability of graphical fonts. Existing quality assessment models can only provide basic visual analyses, such as recognizing clarity and brightness, without in-depth explanations. To address these limitations, we first constructed a large-scale multimodal dataset named the Diversity Font Dataset (DFD), comprising 135,000 font-text pairs. This dataset encompasses a wide range of generated font types and annotations, including language descriptions and quality assessments, thus providing a robust foundation for training and evaluating font analysis models. Based on this dataset, we developed a font agent built upon a Vision-Language Model (VLM) aiming to enhance font quality assessment and offer interpretable question-answering capabilities. Alongside the original visual encoder in VLM, we integrated an Edge-Aware Traces (EAT) module to capture detailed edge information of font strokes and components. Furthermore, we introduced a Dynamic Direct Preference Optimization (D-DPO) strategy to facilitate efficient model fine-tuning. Experimental results demonstrate that Font-Agent achieves state-of-the-art performance on the established dataset. To further evaluate the generalization ability of our algorithm, we conducted additional experiments on several public datasets. The results highlight the notable advantage of Font-Agent in both assessing the quality of generated fonts and comprehending their content.

Coordinated audio generation based on video inputs typically requires a strict audio-visual (AV) alignment, where both semantics and rhythmics of the generated audio segments shall correspond to those in the video frames. Previous studies leverage a two-stage design where the AV encoders are firstly aligned via contrastive learning, then the encoded video representations guide the audio generation process. We observe that both contrastive learning and global video guidance are effective in aligning overall AV semantics while limiting temporally rhythmic synchronization. In this work, we propose Foley-Flow to first align unimodal AV encoders via masked modeling training, where the masked audio segments are recovered under the guidance of the corresponding video segments. After training, the AV encoders which are separately pretrained using only unimodal data are aligned with semantic and rhythmic consistency. Then, we develop a dynamic conditional flow for the final audio generation. Built upon the efficient velocity flow generation framework, our dynamic conditional flow utilizes temporally varying video features as the dynamic condition to guide corresponding audio segment generations. To this end, we extract coherent semantic and rhythmic representations during masked AV alignment, and use this representation of video segments to guide audio generation temporally. Our audio results are evaluated on the standard benchmarks and largely surpass existing results under several metrics. The superior performance indicates that Foley-Flow is effective in generating coordinated audios that are both semantically and rhythmically coherent to various video sequences.

Multi-object tracking (MOT) is a critical task in computer vision, requiring the accurate identification and continuous tracking of multiple objects across video frames. However, current state-of-the-art methods mainly rely on a global optimization technique and multi-stage cascade association strategy, and those approaches often overlook the specific characteristics of assignment task in MOT and useful detection results that may represent occluded objects. To address these challenges, we propose a novel Track-Focused Online Multi-Object Tracker (TrackTrack) with two key strategies: Track-Perspective-Based Association (TPA) and Track-Aware Initialization (TAI). The TPA strategy associates each track with the most suitable detection result by choosing the one with the minimum distance from all available detection results in a track-perspective manner. On the other hand, TAI precludes the generation of spurious tracks in the track-aware aspect by suppressing track initialization of detection results that heavily overlap with current active tracks and more confident detection results. Extensive experiments on MOT17, MOT20, and DanceTrack demonstrate that our TrackTrack outperforms current state-of-the-art trackers, offering improved robustness and accuracy across diverse and challenging tracking scenarios.