| 1 | Deterministic Image-to-Image Translation via Denoising Brownian Bridge Models with Dual Approximators | Bohan Xiao, Peiyong Wang, Qisheng He, Ming Dong | [link](https://openaccess.thecvf.com/content/CVPR2025/html/Xiao_Deterministic_Image-to-Image_Translation_via_Denoising_Brownian_Bridge_Models_with_Dual_CVPR_2025_paper.html) | | 0 | 0 | | | | | | | Image-to-Image (I2I) translation involves converting an im- age from one domain to another. Deterministic I2I transla- tion, such as in image super-resolution, extends this con- cept by guaranteeing that each input generates a consistent and predictable output, closely matching the ground truth (GT) with high fidelity. In this paper, we propose a denois- ing Brownian bridge model with dual approximators (Dual- approx Bridge), a novel generative model that exploits the Brownian bridge dynamics and two neural network-based approximators (one for forward and one for reverse pro- cess) to produce faithful output with negligible variance and high image quality in I2I translations. Our extensive exper- iments on benchmark datasets including image generation and super-resolution demonstrate the consistent and supe- rior performance of Dual-approx Bridge in terms of im- age quality and faithfulness to GT when compared to both stochastic and deterministic baselines. Project page and code: https://github.com/bohan95/dual-app-bridge | 0 |
| 2 | Towards Source-Free Machine Unlearning | Sk Miraj Ahmed, Umit Yigit Basaran, Dripta S. Raychaudhuri, Arindam Dutta, Rohit Kundu, Fahim Faisal Niloy, Basak Guler, Amit K. Roy-Chowdhury | [link](https://openaccess.thecvf.com/content/CVPR2025/html/Ahmed_Towards_Source-Free_Machine_Unlearning_CVPR_2025_paper.html) | | 0 | 0 | | | | | | | As machine learning become more pervasive and data privacy regulations evolve, the ability to remove private or copyrighted information from trained models is becoming an increasingly critical requirement. Existing unlearning methods often rely on the assumption of having access to the entire training dataset during the forgetting process. However, this assumption may not hold true in practical scenarios where the original training data may not be accessible, i.e., the source-free setting. To address this challenge, we focus on the source-free unlearning scenario, where an unlearning algorithm must be capable of removing specific data from a trained model without requiring access to the original training dataset. Building on recent work, we present a method that can estimate the Hessian of the unknown remaining training data, a crucial component required for efficient unlearning. Leveraging this estimation technique, our method enables efficient zero-shot unlearning while providing robust theoretical guarantees on the unlearning performance, while maintaining performance on the remaining data. Extensive experiments over a wide range of datasets verify the efficacy of our method. | 1 |
| 3 | Uni4D: Unifying Visual Foundation Models for 4D Modeling from a Single Video | David Yifan Yao, Albert J. Zhai, Shenlong Wang | [link](https://openaccess.thecvf.com/content/CVPR2025/html/Yao_Uni4D_Unifying_Visual_Foundation_Models_for_4D_Modeling_from_a_CVPR_2025_paper.html) | [2503.21761](https://huggingface.co/papers/2503.21761) | 0 | 0 | | | | | | | This paper presents a unified approach to understanding dynamic scenes from casual videos. Large pretrained vision foundation models, such as vision-language, video depth prediction, motion tracking, and segmentation models, offer promising capabilities. However, training a single model for comprehensive 4D understanding remains challenging. We introduce Uni4D, a multi-stage optimization framework that harnesses multiple pretrained models to advance dynamic 3D modeling, including static/dynamic reconstruction, camera pose estimation, and dense 3D motion tracking. Our results show state-of-the-art performance in dynamic 4D modeling with superior visual quality. Notably, Uni4D requires no retraining or fine-tuning, highlighting the effectiveness of repurposing visual foundation models for 4D understanding. Code and more results are available at: https://davidyao99.github.io/uni4d. | 2 |
| 4 | DynScene: Scalable Generation of Dynamic Robotic Manipulation Scenes for Embodied AI | Sangmin Lee, Sungyong Park, Heewon Kim | [link](https://openaccess.thecvf.com/content/CVPR2025/html/Lee_DynScene_Scalable_Generation_of_Dynamic_Robotic_Manipulation_Scenes_for_Embodied_CVPR_2025_paper.html) | | 0 | 0 | | | | | | | Robotic manipulation in embodied AI critically depends on large-scale, high-quality datasets that reflect realistic object interactions and physical dynamics. However, existing data collection pipelines are often slow, expensive, and heavily reliant on manual efforts. We present DynScene, a diffusion-based framework for generating dynamic robotic manipulation scenes directly from textual instructions. Unlike prior methods that focus solely on static environments or isolated robot actions, DynScene decomposes the generation into two phases static scene synthesis and action trajectory generation allowing fine-grained control and diversity. Our model enhances realism and physical feasibility through scene refinement (layout sampling, quaternion quantization) and leverages residual action representation to enable action augmentation, generating multiple diverse trajectories from a single static configuration. Experiments show DynScene achieves 26.8x faster generation, 1.84x higher accuracy, and 28% greater action diversity than human-crafted data. Furthermore, agents trained with DynScene exhibit up to 19.4% higher success rates across complex manipulation tasks. Our approach paves the way for scalable, automated dataset generation in robot learning. | 3 |
| 5 | DiffLocks: Generating 3D Hair from a Single Image using Diffusion Models | Radu Alexandru Rosu, Keyu Wu, Yao Feng, Youyi Zheng, Michael J. Black | [link](https://openaccess.thecvf.com/content/CVPR2025/html/Rosu_DiffLocks_Generating_3D_Hair_from_a_Single_Image_using_Diffusion_CVPR_2025_paper.html) | [2505.06166](https://huggingface.co/papers/2505.06166) | 0 | 0 | | | | | | | We address the task of generating 3D hair geometry from a single image, which is challenging due to the diversity of hairstyles and the lack of paired image-to-3D hair data. Previous methods are primarily trained on synthetic data and cope with the limited amount of such data by using low-dimensional intermediate representations, such as guide strands and scalp-level embeddings, that require post-processing to decode, upsample, and add realism. These approaches fail to reconstruct detailed hair, struggle with curly hair, or are limited to handling only a few hairstyles. To overcome these limitations, we propose DiffLocks, a novel framework that enables detailed reconstruction of a wide variety of hairstyles directly from a single image. First, we address the lack of 3D hair data by automating the creation of the largest synthetic hair dataset to date, containing 40K hairstyles. Second, we leverage the synthetic hair dataset to learn an image-conditioned diffusion-transfomer model that generates accurate 3D strands from a single frontal image. By using a pretrained image backbone, our method generalizes to in-the-wild images despite being trained only on synthetic data. Our diffusion model predicts a scalp texture map in which any point in the map contains the latent code for an individual hair strand. These codes are directly decoded to 3D strands without post-processing techniques. Representing individual strands, instead of guide strands, enables the transformer to model the detailed spatial structure of complex hairstyles. With this, DiffLocks can recover highly curled hair, like afro hairstyles, from a single image for the first time. Data and code is available at https://radualexandru.github.io/difflocks | 4 |
| 6 | Hyperbolic Category Discovery | Yuanpei Liu, Zhenqi He, Kai Han | [link](https://openaccess.thecvf.com/content/CVPR2025/html/Liu_Hyperbolic_Category_Discovery_CVPR_2025_paper.html) | [2504.06120](https://huggingface.co/papers/2504.06120) | 0 | 0 | | | | | | 0/3 | Generalized Category Discovery (GCD) is an intriguing open-world problem that has garnered increasing attention. Given a dataset that includes both labelled and unlabelled images, GCD aims to categorize all images in the unlabelled subset, regardless of whether they belong to known or unknown classes. In GCD, the common practice typically involves applying a spherical projection operator at the end of the self-supervised pretrained backbone, operating within Euclidean or spherical space. However, both of these spaces have been shown to be suboptimal for encoding samples that possess hierarchical structures. In contrast, hyperbolic space exhibits exponential volume growth relative to radius, making it inherently strong at capturing the hierarchical structure of samples from both seen and unseen categories. Therefore, we propose to tackle the category discovery challenge in the hyperbolic space. We introduce HypCD, a simple Hyperbolic framework for learning hierarchy-aware representations and classifiers for generalized Category Discovery. HypCD first transforms the Euclidean embedding space of the backbone network into hyperbolic space, facilitating subsequent representation and classification learning by considering both hyperbolic distance and the angle between samples. This approach is particularly helpful for knowledge transfer from known to unknown categories in GCD. We thoroughly evaluate HypCD on public GCD benchmarks, by applying it to various baseline and state-of-the-art methods, consistently achieving significant improvements. | 5 |
| 7 | The Language of Motion: Unifying Verbal and Non-verbal Language of 3D Human Motion | Changan Chen, Juze Zhang, Shrinidhi K. Lakshmikanth, Yusu Fang, Ruizhi Shao, Gordon Wetzstein, Li Fei-Fei, Ehsan Adeli | [link](https://openaccess.thecvf.com/content/CVPR2025/html/Chen_The_Language_of_Motion_Unifying_Verbal_and_Non-verbal_Language_of_CVPR_2025_paper.html) | [2412.10523](https://huggingface.co/papers/2412.10523) | 0 | 0 | | | | | | 0/8 | Human communication is inherently multimodal, involving a combination of verbal and non-verbal cues such as speech, facial expressions, and body gestures. Modeling these behaviors is essential for understanding human interaction and for creating virtual characters that can communicate naturally in applications like games, films, and virtual reality. However, existing motion generation models are typically limited to specific input modalities--either speech, text, or motion data--and cannot fully leverage the diversity of available data. In this paper, we propose a novel framework that unifies verbal and non-verbal language using multimodal language models for human motion understanding and generation. This model is flexible in taking text, speech, and motion or any combination of them as input. Coupled with our novel pre-training strategy, our model not only achieves state-of-the-art performance on co-speech gesture generation but also requires much less data for training. Our model also unlocks an array of novel tasks such as editable gesture generation and emotion prediction from motion. We believe unifying the verbal and non-verbal language of human motion is essential for real-world applications, and language models offer a powerful approach to achieving this goal. | 6 |
| 8 | CALICO: Part-Focused Semantic Co-Segmentation with Large Vision-Language Models | Kiet A. Nguyen, Adheesh Juvekar, Tianjiao Yu, Muntasir Wahed, Ismini Lourentzou | [link](https://openaccess.thecvf.com/content/CVPR2025/html/Nguyen_CALICO_Part-Focused_Semantic_Co-Segmentation_with_Large_Vision-Language_Models_CVPR_2025_paper.html) | [2412.19331](https://huggingface.co/papers/2412.19331) | 0 | 0 | | | | | | | Recent advances in Large Vision-Language Models (LVLMs) have enabled general-purpose vision tasks through visual instruction tuning. While existing LVLMs can generate segmentation masks from text prompts for single images, they struggle with segmentation-grounded reasoning across images, especially at finer granularities such as object parts. In this paper, we introduce the new task of part-focused semantic co-segmentation, which involves identifying and segmenting common objects and their constituent common and unique parts across images. To address this task, we present CALICO, the first LVLM designed for multi-image part-level reasoning segmentation. CALICO features two key components, a novel Correspondence Extraction Module that identifies semantic part-level correspondences, and Correspondence Adaptation Modules that embed this information into the LVLM to facilitate multi-image understanding in a parameter-efficient manner. To support training and evaluation, we curate MixedParts, a large-scale multi-image segmentation dataset containing 2.4M samples across 44K images spanning diverse object and part categories. Experimental results demonstrate that CALICO, with just 0.3% of its parameters finetuned, achieves strong performance on this challenging task. | 7 |
| 9 | Task Preference Optimization: Improving Multimodal Large Language Models with Vision Task Alignment | Ziang Yan, Zhilin Li, Yinan He, Chenting Wang, Kunchang Li, Xinhao Li, Xiangyu Zeng, Zilei Wang, Yali Wang, Yu Qiao, Limin Wang, Yi Wang | [link](https://openaccess.thecvf.com/content/CVPR2025/html/Yan_Task_Preference_Optimization_Improving_Multimodal_Large_Language_Models_with_Vision_CVPR_2025_paper.html) | [2412.19326](https://huggingface.co/papers/2412.19326) | 18 | 2 | | | | | | 5/12 ✅ | Current multimodal large language models (MLLMs) struggle with fine-grained or precise understanding of visuals although they give comprehensive perception and reasoning in a spectrum of vision applications. Recent studies either develop tool-using or unify specific visual tasks into the autoregressive framework, often at the expense of overall multimodal performance. To address this issue and enhance MLLMs with visual tasks in a scalable fashion, we propose Task Preference Optimization (TPO), a novel method that utilizes differentiable task preferences derived from typical fine-grained visual tasks. TPO introduces learnable task tokens that establish connections between multiple task-specific heads and the MLLM. By leveraging rich visual labels during training, TPO significantly enhances the MLLM's multimodal capabilities and task-specific performance. Through multi-task co-training within TPO, we observe synergistic benefits that elevate individual task performance beyond what is achievable through single-task training methodologies. Our instantiation of this approach with VideoChat and LLaVA demonstrates an overall 14.6% improvement in multimodal performance compared to baseline models. Additionally, MLLM-TPO demonstrates robust zero-shot capabilities across various tasks, performing comparably to state-of-the-art supervised models. | 8 |
| 10 | Cross-modal Causal Relation Alignment for Video Question Grounding | Weixing Chen, Yang Liu, Binglin Chen, Jiandong Su, Yongsen Zheng, Liang Lin | [link](https://openaccess.thecvf.com/content/CVPR2025/html/Chen_Cross-modal_Causal_Relation_Alignment_for_Video_Question_Grounding_CVPR_2025_paper.html) | [2503.07635](https://huggingface.co/papers/2503.07635) | 0 | 0 | | | | | | 0/6 | Video question grounding (VideoQG) requires models to answer the questions and simultaneously infer the relevant video segments to support the answers. However, existing VideoQG methods usually suffer from spurious cross-modal correlations, leading to a failure to identify the dominant visual scenes that align with the intended question. Moreover, vision-language models exhibit unfaithful generalization performance and lack robustness on challenging downstream tasks such as VideoQG. In this work, we propose a novel VideoQG framework named Cross-modal Causal Relation Alignment (CRA), to eliminate spurious correlations and improve the causal consistency between question-answering and video temporal grounding. Our CRA involves three essential components: i) Gaussian Smoothing Grounding (GSG) module for estimating the time interval via cross-modal attention, which is de-noised by an adaptive Gaussian filter, ii) Cross-Modal Alignment (CMA) enhances the performance of weakly supervised VideoQG by leveraging bidirectional contrastive learning between estimated video segments and QA features, iii) Explicit Causal Intervention (ECI) module for multimodal deconfounding, which involves front-door intervention for vision and back-door intervention for language. Extensive experiments on two VideoQG datasets demonstrate the superiority of our CRA in discovering visually grounded content and achieving robust question reasoning. Codes are available at https://github.com/WissingChen/CRA-GQA. | 9 |
| 11 | Words or Vision: Do Vision-Language Models Have Blind Faith in Text? | Ailin Deng, Tri Cao, Zhirui Chen, Bryan Hooi | [link](https://openaccess.thecvf.com/content/CVPR2025/html/Deng_Words_or_Vision_Do_Vision-Language_Models_Have_Blind_Faith_in_CVPR_2025_paper.html) | [2503.02199](https://huggingface.co/papers/2503.02199) | 8 | 2 | | | | | | 2/4 ✅ | Vision-Language Models (VLMs) excel in integrating visual and textual information for vision-centric tasks, but their handling of inconsistencies between modalities is underexplored. We investigate VLMs' modality preferences when faced with visual data and varied textual inputs in vision-centered settings.By introducing textual variations to four vision-centric tasks and evaluating ten Vision-Language Models (VLMs), we discover a "blind faith in text" phenomenon: VLMs disproportionately trust textual data over visual data when inconsistencies arise, leading to significant performance drops under corrupted text and raising safety concerns.We analyze factors influencing this text bias, including instruction prompts, language model size, text relevance, token order, and the interplay between visual and textual certainty. While certain factors, such as scaling up the language model size, slightly mitigate text bias, others like token order can exacerbate it due to positional biases inherited from language models. To address this issue, we explore supervised fine-tuning with text augmentation and demonstrate its effectiveness in reducing text bias. Additionally, we provide a theoretical analysis suggesting that the blind faith in text phenomenon may stem from an imbalance of pure text and multi-modal data during training.Our findings highlight the need for balanced training and careful consideration of modality interactions in VLMs to enhance their robustness and reliability in handling multi-modal data inconsistencies. | 10 |