ICCV 2025 Papers

Scene coordinate regression (SCR) has established itself as a promising learning-based approach to visual relocalization. After mere minutes of scene-specific training, SCR models estimate camera poses of query images with high accuracy. Still, SCR methods fall short of the generalization capabilities of more classical feature-matching approaches. When imaging conditions of query images, such as lighting or viewpoint, are too different from the training views, SCR models fail. Failing to generalize is an inherent limitation of previous SCR frameworks, since their training objective is to encode the training views in the weights of the coordinate regressor itself. The regressor essentially overfits to the training views, by design. We propose to separate the coordinate regressor and the map representation into a generic transformer and a scene-specific map code. This separation allows us to pre-train the transformer on tens of thousands of scenes. More importantly, it allows us to train the transformer to generalize from mapping images to unseen query images during pre-training. We demonstrate on multiple challenging relocalization datasets that our method, ACE-G, leads to significantly increased robustness while keeping the computational footprint attractive.

Dense visual prediction tasks, such as detection and segmentation, are crucial for time-critical applications (e.g., autonomous driving and video surveillance). While deep models achieve strong performance, their efficiency remains a challenge. Knowledge distillation (KD) is an effective model compression technique, but existing feature-based KD methods rely on static, teacher-driven feature selection, failing to adapt to the student's evolving learning state or leverage dynamic student-teacher interactions. To address these limitations, we propose Adaptive student-teacher Cooperative Attention Masking for Knowledge Distillation (ACAM-KD), which introduces two key components: (1) Student-Teacher Cross-Attention Feature Fusion (STCA-FF), which adaptively integrates features from both models for a more interactive distillation process, and (2) Adaptive Spatial-Channel Masking (ASCM), which dynamically generates importance masks to enhance both spatial and channel-wise feature selection. Unlike conventional KD methods, ACAM-KD adapts to the student's evolving needs throughout the entire distillation process. Extensive experiments on multiple benchmarks validate its effectiveness. For instance, on COCO2017, ACAM-KD improves object detection performance by up to 1.4 mAP over the state-of-the-art when distilling a ResNet-50 student from a ResNet-101 teacher. For semantic segmentation on Cityscapes, it boosts mIoU by 3.09 over the baseline with DeepLabV3-MobileNetV2 as the student model.

Although 3D Gaussian Splatting (3DGS) has revolutionized 3D reconstruction, it still faces challenges such as aliasing, projection artifacts, and view inconsistencies, primarily due to the simplification of treating splats as 2D entities. We argue that incorporating full 3D evaluation of Gaussians throughout the 3DGS pipeline can effectively address these issues while preserving rasterization efficiency. Specifically, we introduce an adaptive 3D smoothing filter to mitigate aliasing and present a stable view-space bounding method that eliminates popping artifacts when Gaussians extend beyond the view frustum. Furthermore, we promote tile-based culling to 3D with screen-space planes, accelerating rendering and reducing sorting costs for hierarchical rasterization. Our method achieves state-of-the-art quality on in-distribution evaluation sets and significantly outperforms other approaches for out-of-distribution views. Our qualitative evaluations further demonstrate the effective removal of aliasing, distortions, and popping artifacts, ensuring real-time, artifact-free rendering.

Recently, the field of 3D scene stylization has attracted considerable attention, particularly for applications in the metaverse. A key challenge is rapidly transferring the style of an arbitrary reference image to a 3D scene while faithfully preserving its content structure and spatial layout. Works leveraging implicit representations with gradient-based optimization achieve impressive style transfer results, yet the lengthy processing time per individual style makes rapid switching impractical. In this paper, we propose A^3GS, a novel feed-forward neural network for zero-shot 3DGS stylization that enables transferring any image style to arbitrary 3D scenes in just 10 seconds without the need for per-style optimization. Our work introduces a Graph Convolutional Network (GCN)-based autoencoder aimed at efficient feature aggregation and decoding of spatially structured 3D Gaussian scenes. The encoder converts 3DGS scenes into a latent space. Furthermore, for the latent space, we utilize Adaptive Instance Normalization (AdaIN) to inject features from the target style image into the 3D Gaussian scene. Finally, we constructed a 3DGS dataset using a generative model and proposed a two-stage training strategy for A^3GS. Owing to the feed-forward design, our framework can perform fast style transfer on large-scale 3DGS scenes, which poses a severe challenge to the memory consumption of optimization-based methods. Extensive experiments demonstrate that our approach achieves high-quality, consistent 3D stylization in seconds.

Vision-language models (VLMs) often struggle with compositional reasoning due to insufficient high-quality image-text data. To tackle this challenge, we propose a novel block-based diffusion approach that automatically generates counterfactual datasets without manual annotation. Our method utilizes large language models to identify entities and their spatial relationships. It then independently generates image blocks as "puzzle pieces" coherently arranged according to specified compositional rules. This process creates diverse, high-fidelity counterfactual image-text pairs with precisely controlled variations. In addition, we introduce a specialized loss function that differentiates inter-set from intra-set samples, enhancing training efficiency and reducing the need for negative samples. Experiments demonstrate that fine-tuning VLMs with our counterfactual datasets significantly improves visual reasoning performance. Our approach achieves state-of-the-art results across multiple benchmarks while using substantially less training data than existing methods.

Neural Radiance Fields (NeRF) has emerged as a compelling framework for scene representation and 3D recovery. To improve its performance on real-world data, depth regularizations have proven to be the most effective ones. However, depth estimation models not only require expensive 3D supervision in training, but also suffer from generalization issues. As a result, the depth estimations can be erroneous in practice, especially for outdoor unbounded scenes. In this paper, we propose to employ view-consistent distributions instead of fixed depth value estimations to regularize NeRF training. Specifically, the distribution is computed by utilizing both low-level color features and high-level distilled features from foundation models at the projected 2D pixel-locations from per-ray sampled 3D points. By sampling from the view-consistency distributions, an implicit regularization is imposed on the training of NeRF. We also propose a novel depth-pushing loss that works in conjunction with the sampling technique to jointly provide effective regularizations for eliminating the failure modes. Extensive experiments conducted on various scenes from public datasets demonstrate that our proposed method can generate significantly better novel view synthesis results than state-of-the-art NeRF variants as well as different depth regularization methods.

This paper explains training-time out-of-distribution (OOD) detection from a novel view, i.e., interactions between different input variables of deep neural networks (DNNs). Specifically, we provide a unified understanding of the effectiveness of current training-time OOD detection methods, i.e., DNNs trained with these methods all encode more complex interactions for inference than those trained without training-time methods, which contributes to their superior OOD detection performance. We further conduct thorough empirical analyses and verify that complex interactions play a primary role in OOD detection, by developing a simple-yet-efficient method to force the DNN to learn interactions of specific complexities and evaluate the change of OOD detection performances. Besides, we also use interactions to investigate why near-OOD samples are more difficult to distinguish from in-distribution (ID) samples than far-OOD samples, mainly because compared to far-OOD samples, the distribution of interactions in near-OOD samples is more similar to that of ID samples. Moreover, we discover that training-time OOD detection methods can effectively decrease such similarities.

Incomplete multi-view clustering (IMVC) has gained increasing attention due to its ability to analyze incomplete multi-view data.Despite deep IMVC methods achieved significant progress, they still face two challenges: (I) The method-specific inseparable designs limit their application. (II) Non-independent and identically distributed (Non-IID) missing patterns has not been considered and caused degeneration. To address these issues, we propose a novel unified framework that bridges from deep MVC to deep IMVC, while emphasizing the robustness against Non-IID missing patterns. Our framework has a two-stage process: (I) Multi-view learning on complete data, where our framework is modularly established to be compatible with different multi-view interaction objectives. (II) Transfer learning and clustering on incomplete data, where we propose a multi-view domain adversarial learning method to improve the model robustness to Non-IID missing patterns. Moreover, an intra-view and inter-view imputation strategy is introduced for more reliable clustering.Based on our unified framework, we easily construct multiple IMVC instances and extensive experiments verified their clustering effectiveness.

Recent advancements in large language models (LLMs) have significantly improved their ability to generate natural and contextually appropriate text, enabling more human-like interactions. However, understanding and generating interactive human-like motion, especially involving coordinated interactive motion, remains a challenging problem due to its inherent complexity. To address this, we present MoLaM, the Interactive Motion-LAnguage Model, a unified architecture that jointly processes language and motion modalities for understanding, generating, and controlling interactive motions in multi-turn conversational settings. Unlike prior approaches limited to uni-directional tasks (e.g., text-to-motion or motion-to-text), MoLaM supports a wide range of bi-directional and multi-turn tasks. We also introduce Inter-MT2, a large-scale instruction tuning dataset containing 82.7K multi-turn interactive motion instructions and 153K motion samples, covering tasks such as editing, question answering, and story generation. Leveraging LLMs and motion diffusion models, MoLaM demonstrates strong performance across five interactive motion tasks: motion-to-text, text-to-motion, reaction generation, motion editing, and motion reasoning, outperforming or matching task-specific baselines with a single, unified model.

In recent years, general visual foundation models (VFMs) have witnessed increasing adoption, particularly as image encoders for popular multi-modal large language models (MLLMs). However, without semantically fine-grained supervision, these models still encounter fundamental prediction errors in the context of downstream text-image-related tasks, i.e., perception, understanding and reasoning with images containing small and dense texts. To bridge this gap, we develop TokenFD, the first token-level visual foundation model specifically tailored for text-image-related tasks, designed to support a variety of traditional downstream applications. To facilitate the pretraining of TokenFD, we also devise a high-quality data production pipeline that constructs the first token-level image text dataset, TokenIT, comprising 20 million images and 1.8 billion token-mask pairs. Furthermore, leveraging this foundation with exceptional image-as-text capability, we seamlessly replace previous VFMs with TokenFD to construct a token-level visual-language MLLM, TokenVL, for VQA-based document understanding tasks. Finally, extensive experiments demonstrate the effectiveness of TokenFD and TokenVL. Code, demo, datasets, and weights are available at https://github.com/Token-family/TokenFD.

Long-Tailed Class-Incremental Learning (LT-CIL) remains a fundamental challenge due to biased gradient updates caused by highly imbalanced data distributions and the inherent stability-plasticity dilemma. These factors jointly degrade tail-class performance and exacerbate catastrophic forgetting. To tackle these issues, we propose Geometric Prototype Alignment (GPA), a model-agnostic approach that calibrates classifier learning dynamics via geometric feature-space alignment. GPA initializes classifier weights by projecting frozen class prototypes onto a unit hypersphere, thereby disentangling magnitude imbalance from angular discriminability. During incremental updates, a Dynamic Anchoring mechanism adaptively adjusts classifier weights to preserve geometric consistency, effectively balancing plasticity for new classes with stability for previously acquired knowledge. Integrated into state-of-the-art CIL frameworks such as LUCIR and DualPrompt, GPA yields substantial gains, improving average incremental accuracy by 6.11% and reducing forgetting rates by 6.38% on CIFAR100-LT. Theoretical analysis further demonstrates that GPA accelerates convergence by 2.7X and produces decision boundaries approaching Fisher-optimality. Our implementation is available at https://github.com/laixinyi023/Geometric-Prototype-Alignment.

Recent Mamba-based methods for the pose-lifting task tend to model joint dependencies by 2D-to-1D mapping with diverse scanning strategies. Though effective, they struggle to model intricate joint connections and uniformly process all joint motion trajectories while neglecting the intrinsic differences across motion characteristics. In this work, we propose a structure-aware and motion-adaptive framework to capture spatial joint topology along with diverse motion dynamics independently, named as SAMA. Specifically, SAMA consists of a Structure-aware State Integrator (SSI) and a Motion-adaptive State Modulator (MSM). The Structure-aware State Integrator is tasked with leveraging dynamic joint relationships to fuse information at both the joint feature and state levels in the state space, based on pose topology rather than sequential state transitions. The Motion-adaptive State Modulator is responsible for joint-specific motion characteristics recognition, thus applying tailored adjustments to diverse motion patterns across different joints. Through the above key modules, our algorithm enables structure-aware and motion-adaptive pose lifting. Extensive experiments across multiple benchmarks demonstrate that our algorithm achieves advanced results with fewer computational costs.

Diffusion models have demonstrated powerful capability as a versatilist for dense vision tasks, yet the generalization ability to unseen domains remains rarely explored. This paper presents HarDiff, an efficient frequency learning scheme, so as to advance generalizable paradigms for diffusion based dense prediction. It draws inspiration from a fine-grained analysis of Discrete Hartley Transform, where some low-frequency features activate the broader content of an image, while some high-frequency features maintain sufficient details for dense pixels. Consequently, HarDiff consists of two key components. The low-frequency training process extracts structural priors from the source domain, to enhance understanding of task-related content. The high-frequency sampling process utilizes detail-oriented guidance from the unseen target domain, to infer precise dense predictions with target-related details. Extensive empirical evidence shows that HarDiff can be easily plugged into various dense vision tasks, e.g., semantic segmentation, depth estimation and haze removal, yielding improvements over the state-of-the-art methods in twelve public benchmarks.

We introduce a recipe for generating immersive 3D worlds from a single image by framing the task as an in-context learning problem for 2D inpainting models. This approach requires minimal training and uses existing generative models. Our process involves two steps: generating coherent panoramas using a pre-trained diffusion model and lifting these into 3D with a metric depth estimator. We then fill unobserved regions by conditioning the inpainting model on rendered point clouds, requiring minimal fine-tuning. Tested on both synthetic and real images, our method produces high-quality 3D environments suitable for VR display. By explicitly modeling the 3D structure of the generated environment from the start, our approach consistently outperforms state-of-the-art, video synthesis-based methods along multiple quantitative image quality metrics.

Inverse rendering aims to reconstruct geometry and reflectance from captured images. Display-camera imaging systems offer unique advantages for this task: each pixel can easily function as a programmable point light source, and the polarized light emitted by LCD displays facilitates diffuse-specular separation. Despite these benefits, there is currently no public real-world dataset captured using display-camera systems, unlike other setups such as light stages. This absence hinders the development and evaluation of display-based inverse rendering methods. In this paper, we introduce the first real-world dataset for display-based inverse rendering. To achieve this, we construct and calibrate an imaging system comprising an LCD display and stereo polarization cameras. We then capture a diverse set of objects with diverse geometry and reflectance under one-light-at-a-time (OLAT) display patterns. We also provide high-quality ground-truth geometry. Our dataset enables the synthesis of captured images under arbitrary display patterns and different noise levels. Using this dataset, we evaluate the performance of existing photometric stereo and inverse rendering methods, and provide a simple, yet effective baseline for display inverse rendering, outperforming state-of-the-art inverse rendering methods.Code and dataset are available on our project page at https://michaelcsj.github.io/DIR/.

Whole-body biometric recognition is a challenging multi-modal task that integrates various biometric modalities, including face, gait, and body. This integration is essential for overcoming the limitations of unimodal systems. Traditionally, whole-body recognition involves deploying different models to process multiple modalities, achieving the final outcome by score-fusion (e.g., weighted averaging similarity matrices from each model). However, these conventional methods may overlook the variations in score distributions of individual modalities, making it challenging to improve final performance. In this work, we present Quality-guided Mixture of score-fusion Experts (QME), a novel framework designed for improving whole-body biometric recognition performance through a learnable score-fusion strategy using a Mixture of Experts (MoE). We introduce a novel pseudo quality loss for quality estimation with a modality-specific Quality Estimator (QE), and a score triplet loss to improve the metric performance. Extensive experiments on multiple whole-body biometric datasets demonstrate the effectiveness of our proposed approach, achieving state-of-the-art results across various metrics compared to baseline methods. Our method is effective for multi-modal and multi-model, addressing key challenges such as model misalignment in the similarity score domain and variability in data quality. Code is available at the \href https://github.com/jiezhu23/QME_ICCV25 Project Link

Extracting physically plausible 3D human motion from videos is a critical task. Although existing simulation-based motion imitation methods can enhance the physical quality of daily motions estimated from monocular video capture, extending this capability to high-difficulty motions remains an open challenge. This can be attributed to some flawed motion clips in video-based motion capture results and the inherent complexity in modeling high-difficulty motions. Therefore, sensing the advantage of segmentation in localizing human body, we introduce a mask-based motion correction module (MCM) that leverages motion context and video mask to repair flawed motions; and propose a physics-based motion transfer module (PTM), which employs a prior injected pretrain and adapt approach for motion imitation, improving physical plausibility with the ability to handle in-the-wild and challenging motions. Our approach is designed as a plug-and-play module to physically refine the video motion capture, which also excels in motion generation tasks. Finally, we collected a challenging in-the-wild test set to establish a benchmark, and our method has demonstrated effectiveness on both the new benchmark and existing public datasets. Our project page is : https://physicalmotionrestoration.github.io/