ICCV 2025 Papers

Video data inherently captures rich, dynamic contexts that reveal objects in varying poses, interactions, and state transitions, offering rich potential for unsupervised object representation learning. However, most prior representation learning methods rely on static image datasets like ImageNet, which lack temporal cues and only provide high-level semantic supervision. Meanwhile, existing natural video datasets are not ideal for learning object-centric representations due to limited object focus and class diversity. To explore unsupervised object representation learning grounded in object dynamics--beyond static appearance--we introduce TrackVerse, a large-scale video dataset of 31.9 million object tracks spanning over 1,000 categories, each capturing the motion, appearance, and evolving states of an object over time. We further propose a variance-aware contrastive learning framework that adapts to data augmentations, encouraging the model to learn state-sensitive features. Extensive experiments demonstrate that representations learned from TrackVerse with variance-aware contrastive learning significantly outperform those from static image datasets and non-object-centric natural video across multiple downstream tasks including object/attributie recognition, action recognition and video instance segmentation, highlighting the rich semantic and state content in TrackVerse feature.

3D LiDAR-based single object tracking (SOT) relies on sparse and irregular point clouds, posing challenges from geometric variations in scale, motion patterns, and structural complexity across object categories. Current category-specific approaches achieve good accuracy but are impractical for real-world use, requiring separate models for each category and showing limited generalization. To tackle these issues, we propose TrackAny3D, the first framework to transfer large-scale pretrained 3D models for category-agnostic 3D SOT. We first integrate parameter-efficient adapters to bridge the gap between pretraining and tracking tasks while preserving geometric priors. Then, we introduce a Mixture-of-Geometry-Experts (MoGE) architecture that adaptively activates specialized subnetworks based on distinct geometric characteristics. Additionally, we design a temporal context optimization strategy that incorporates learnable temporal tokens and a dynamic mask weighting module to propagate historical information and mitigate temporal drift. Experiments on three commonly-used benchmarks show that TrackAny3D establishes new state-of-the-art performance on category-agnostic 3D SOT, demonstrating strong generalization and competitiveness. We hope this work will enlighten the community on the importance of unified models and further expand the use of large-scale pretrained models in this field.

Image Copy Detection (ICD) aims to identify manipulated content between image pairs through robust feature representation learning. While self-supervised learning (SSL) has advanced ICD systems, existing view-level contrastive methods struggle with sophisticated edits due to insufficient fine-grained correspondence learning. We address this limitation by exploiting the inherent geometric traceability in edited content through two key innovations. First, we propose PixTrace - a pixel coordinate tracking module that maintains explicit spatial mappings across editing transformations. Second, we introduce CopyNCE, a geometrically-guided contrastive loss that regularizes patch affinity using overlap ratios derived from PixTrace's verified mappings. Our method bridges pixel-level traceability with patch-level similarity learning, suppressing supervision noise in SSL training. Extensive experiments demonstrate not only state-of-the-art performance (88.7% mAP / 83.9% RP90 for matcher, 72.6% mAP / 68.4% RP90 for descriptor on DISC21 dataset) but also better interpretability over existing methods. Code is available.

We address the challenge of lifting 2D visual segmentation to 3D in Gaussian Splatting. Existing methods often suffer from inconsistent 2D masks across viewpoints and produce noisy segmentation boundaries as they neglect these semantic cues to refine the learned Gaussians. To overcome this, we introduce Gaussian Instance Tracing (GIT), which augments the standard Gaussian representation with an instance weight matrix across input views. Leveraging the inherent consistency of Gaussians in 3D, we use this matrix to identify and correct 2D segmentation inconsistencies. Furthermore, since each Gaussian ideally corresponds to a single object, we propose a GIT-guided adaptive density control mechanism to split and prune ambiguous Gaussians during training, resulting in sharper and more coherent 2D and 3D segmentation boundaries. Experimental results show that our method extracts clean 3D assets and consistently improves 3D segmentation in both online (e.g., self-prompting) and offline (e.g., contrastive lifting) settings, enabling applications such as hierarchical segmentation, object extraction, and scene editing.

Image degradation synthesis is highly desirable in a wide variety of applications ranging from image restoration to simulating artistic effects. Existing models are designed to generate one specific or a narrow set of degradations, which often require user-provided degradation parameters. As a result, they lack the generalizability to synthesize degradations beyond their initial design or adapt to other applications. Here we propose the first universal degradation model that can synthesize a broad spectrum of complex and realistic degradations containing both homogeneous (global) and inhomogeneous (spatially varying) components. Our model automatically extracts and disentangles homogeneous and inhomogeneous degradation features, which are later used for degradation synthesis without user intervention. A disentangle-by-compression method is proposed to separate degradation information from images. Two novel modules for extracting and incorporating inhomogeneous degradations are created to model inhomogeneous components in complex degradations. We demonstrate the model's accuracy and adaptability in film-grain simulation and blind image restoration tasks. The demo video, code, and dataset of this project will be released at Yang's GitHub account.

Variations in medical imaging modalities and individual anatomical differences pose challenges to cross-modality generalization in multi-modal tasks. Existing methods often concentrate exclusively on common anatomical patterns, thereby neglecting individual differences and consequently limiting their generalization performance. This paper emphasizes the critical role of learning individual-level invariance, i.e., personalized representation \mathbb X _h, to enhance multi-modality generalization under both homogeneous and heterogeneous settings.It reveals that mappings from individual anatomy to different medical modalities remain static across the population, which is implied in the personalization process.We propose a two-stage approach: pre-training with invariant representation \mathbb X _h for personalization, then fine-tuning for diverse downstream tasks.We provide both theoretical and empirical evidence demonstrating the feasibility and advantages of personalization, showing that our approach yields greater generalizability and transferability across diverse multi-modal medical tasks compared to methods lacking personalization. Extensive experiments further validate that our approach significantly enhances performance in various generalization scenarios.

Advances in Earth observation (EO) foundation models have unlocked the potential of big satellite data to learn generic representations from space, benefiting a wide range of downstream applications crucial to our planet. However, most existing efforts remain limited to fixed spectral sensors, focus solely on the Earth's surface, and overlook valuable metadata beyond imagery. In this work, we take a step towards next-generation EO foundation models with three key components: 1) Copernicus-Pretrain, a massive-scale pretraining dataset that integrates 18.7M aligned images from all major Copernicus Sentinel missions, spanning from the Earth's surface to its atmosphere; 2) Copernicus-FM, a unified foundation model capable of processing any spectral or non-spectral sensor modality using extended dynamic hypernetworks and flexible metadata encoding; and 3) Copernicus-Bench, a systematic evaluation benchmark with 15 hierarchical downstream tasks ranging from preprocessing to specialized applications for each Sentinel mission. Our dataset, model, and benchmark greatly improve the scalability, versatility, and multimodal adaptability of EO foundation models, while also creating new opportunities to connect EO, weather, and climate research. Codes at https://github.com/zhu-xlab/Copernicus-FM.

Deep neural networks for 3D point clouds have been demonstrated to be vulnerable to adversarial examples. Previous 3D adversarial attack methods often exploit certain information about the target models, such as model parameters or outputs, to generate adversarial point clouds. However, in realistic scenarios, it is challenging to obtain any information about the target models under conditions of absolute security. Therefore, we focus on transfer-based attacks, where generating adversarial point clouds does not require any information about the target models. Based on our observation that the critical features used for point cloud classification are consistent across different DNN architectures, we propose CFG, a novel transfer-based black-box attack method that improves the transferability of adversarial point clouds via the proposed **C**ritical **F**eature **G**uidance. Specifically, our method regularizes the search of adversarial point clouds by computing the importance of the extracted features, prioritizing the corruption of critical features that are likely to be adopted by diverse architectures. Further, we explicitly constrain the maximum deviation extent of the generated adversarial point clouds in the loss function to ensure their imperceptibility. Extensive experiments conducted on the ModelNet40 and ScanObjectNN benchmark datasets demonstrate that the proposed CFG outperforms the state-of-the-art attack methods by a large margin. The code is available at https://github.com/AIASLab/CFG-ICCV2025.

The growing presence of vision-based systems in the physical world comes with a major requirement: highly accurate estimation of the pose, a task typically addressed through methods based on local features. The totality of the available feature-based localization solutions are designed under the assumption of using the same feature for mapping and localization. However, as the implementation provided by each vendor is based on heterogeneous feature extraction algorithms, collaboration between different devices is not straightforward or even not possible. Although there are some alternatives, such as re-extracting the features or reconstructing the image from them, these are impractical or costly to implement in a real pipeline. To overcome this, and inspired in the seminal work Cross-Descriptor [12], we propose Cross-Feature, a method that applies a patch-based training strategy to a simple MLP which projects features to a common embedded space. As a consequence, our proposal allows to establish suitable correspondences between features computed through heterogeneous algorithms, e.g., SIFT [23] and SuperPoint [9]. We experimentally demonstrate the validity of Cross-Feature by evaluating it in tasks as Image Matching, Visual Localization and a new Collaborative Visual Localization and Mapping scenario. We believe this is the first step towards full Visual Localization interoperability. Code and data will be made available.

Human intelligence requires both correctness and robustness, with the former being foundational for the latter. In video understanding, correctness ensures the accurate interpretation of visual content, and robustness maintains consistent performance in challenging conditions. Despite advances in video large language models (video LLMs), existing benchmarks inadequately reflect the gap between these models and human intelligence in maintaining correctness and robustness in video interpretation. We introduce the Video Turing Test (Video-TT), a benchmark designed to assess if video LLMs can interpret real-world videos as effectively as humans.Video-TT differentiates between errors due to inadequate frame sampling and 1) genuine gaps in understanding complex visual narratives, and 2) evaluates robustness against natural adversarial questions. Video-TT comprises 1,000 YouTube Shorts videos, each with one open-ended question and four adversarial questions that probe visual and narrative complexity. Our evaluation shows a significant gap between video LLMs and human performance, underscoring the need for benchmarks like Video-TT to advance video understanding.

Diffusion Transformers (DiT) have emerged as a powerful architecture for image and video generation, offering superior quality and scalability. However, their practical application suffers from inherent dynamic feature instability, leading to error amplification during cached inference. Through systematic analysis, we identify the absence of long-range feature preservation mechanisms as the root cause of unstable feature propagation and perturbation sensitivity. To this end, we propose Skip-DiT, a novel DiT variant enhanced with Long-Skip-Connections (LSCs) - the key efficiency component in U-Nets. Theoretical spectral norm and visualization analysis demonstrate how LSCs stabilize feature dynamics. Skip-DiT architecture and its stabilized dynamic feature enable an efficient statical caching mechanism that reuses deep features across timesteps while updating shallow components. Extensive experiments across image and video generation tasks demonstrate that Skip-DiT achieves: (1) **4.4x** training acceleration and faster convergence, (2) **1.5-2x** inference acceleration without quality loss and high fidelity to original output, outperforming existing DiT caching methods across various quantitative metrics. Our findings establish long-skip connections as critical architectural components for training stable and efficient diffusion transformers. Codes are provided in the anonymous URL https://anonymous.4open.science/r/Skip-DiT-72B7/.

Spatial intelligence is emerging as a transformative frontier in AI, yet it remains constrained by the scarcity of large-scale 3D datasets. Unlike the abundant 2D imagery, acquiring 3D data typically requires specialized sensors and laborious annotation. In this work, we present a scalable pipeline that converts single-view images into comprehensive, scale- and appearance-realistic 3D representations -- including point clouds, camera poses, depth maps, and pseudo-RGBD -- via integrated depth estimation, camera calibration, and scale calibration. Our method bridges the gap between the vast repository of imagery and the increasing demand for spatial scene understanding. By automatically generating authentic, scale-aware 3D data from images, we significantly reduce data collection costs and open new avenues for advancing spatial intelligence. We release two generated spatial datasets, i.e., COCO-3D and Objects365-v2-3D, and demonstrate through extensive experiments that our generated data can benefit various 3D tasks, ranging from fundamental perception to MLLM-based reasoning. These results validate our pipeline as an effective solution for developing AI systems capable of perceiving, understanding, and interacting with physical environments.

Autonomous driving (AD) systems are becoming increasingly capable of handling complex tasks, mainly due to recent advances in deep learning and AI. As interactions between autonomous systems and humans increase, the interpretability of decision-making processes in driving systems becomes increasingly crucial for ensuring safe driving operations. Successful human-machine interaction requires understanding the underlying representations of the environment and the driving task, which remains a significant challenge in deep learning-based systems. To address this, we introduce the task of interpretability in maneuver prediction before they occur for driver safety, i.e., driver intent prediction (DIP), which plays a critical role in AD systems. To foster research in interpretable DIP, we curate the eXplainable Driving Action Anticipation Dataset (DAAD-X), a new multimodal, ego-centric video dataset to provide hierarchical, high-level textual explanations as causal reasoning for the driver's decisions. These explanations are derived from both the driver's eye-gaze and the ego-vehicle's perspective. Next, we propose Video Concept Bottleneck Model (VCBM), a framework that generates spatio-temporally coherent explanations inherently, without relying on post-hoc techniques. Finally, through extensive evaluations of the proposed VCBM on the DAAD-X dataset, we demonstrate that transformer-based models exhibit greater interpretability than conventional CNN-based models. Additionally, we introduce a multilabel t-SNE visualization technique to illustrate the disentanglement and causal correlation among multiple explanations.

Person search aims to simultaneously detect and re-identify a query person within an entire scene. While existing studies have made significant progress in achieving superior performance on clean datasets, the challenge of robustness under various corruptions remains largely unexplored. However, the lack of proper testing environments for corrupted conditions persists as a challenge, since extensive collection of new person images attempting to cover numerous corruption scenarios inevitably introduces privacy concerns. In this context, we establish an evaluation framework for analyzing corruption robustness using existing publicly available data, and introduce two new benchmarks: CUHK-SYSU-C and PRW-C. Based on this framework incorporating 18 corruptions with 5 severity levels each, we conduct an extensive robustness evaluation of popular person search methods. Moreover, we explore a straightforward solution that naturally arises: integrating corruption-robust detection and re-identification models. Our experiments reveal that existing person search models remain highly vulnerable to corruption, and this issue is not resolved by the simple integration approach. To analyze the underlying reasons, we further investigate the vulnerability of the detection and representation stages to corruption and explore its impact on both foreground and background areas. Based on these analyses, we propose a foreground-aware augmentation and corresponding robust proposal regularizer to enhance the robustness of person search models. Supported by our comprehensive robustness analysis and evaluation framework our benchmarks provide, our proposed technique substantially improves the robustness of existing person search models.

Diffusion models like Stable Diffusion have become prominent in visual synthesis tasks due to their powerful customization capabilities, which also introduce significant security risks, including deepfakes and copyright infringement. In response, a class of methods known as protective perturbation emerged, which mitigates image misuse by injecting imperceptible adversarial noise. However, purification can remove protective perturbations, thereby exposing images again to the risk of malicious forgery. In this work, we formalize the anti-purification task, highlighting challenges that hinder existing approaches, and propose a simple diagnostic protective perturbation named AntiPure. AntiPure exposes vulnerabilities of purification within the "purification-customization" workflow, owing to two guidance mechanisms: 1) Patch-wise Frequency Guidance, which reduces the model's influence over high-frequency components in the purified image, and 2) Erroneous Timestep Guidance, which disrupts the model's denoising strategy across different timesteps. With additional guidance, AntiPure embeds imperceptible perturbations that persist under representative purification settings, achieving effective post-customization distortion. Experiments show that, as a stress test for purification, AntiPure achieves minimal perceptual discrepancy and maximal distortion, outperforming other protective perturbation methods within the purification-customization workflow.

So-called unsupervised anomaly detection is better described as semi-supervised, as it assumes all training data are nominal. This assumption simplifies training but requires manual data curation, introducing bias and limiting adaptability. We propose Confident Meta-learning (CoMet), a novel training strategy that enables deep anomaly detection models to learn from uncurated datasets where nominal and anomalous samples coexist, eliminating the need for explicit filtering. Our approach integrates Soft Confident Learning, which assigns lower weights to low-confidence samples, and Meta-Learning, which stabilizes training by regularizing updates based on training-validation loss covariance. This prevents overfitting and enhances robustness to noisy data. CoMet is model-agnostic and can be applied to any anomaly detection method trainable via gradient descent. Experiments on MVTec-AD, VIADUCT, and KSDD2 with two state-of-the-art models demonstrate the effectiveness of our approach, consistently improving over the baseline methods, remaining insensitive to anomalies in the training set, and setting a new state-of-the-art across all datasets.