International Journal of Computer Vision最新文献

{"title":"Achieving High-Fidelity and Consistent Super-Resolution in Pathological Images using a Novel Consistency-Restricted Diffusion Framework","authors":"Hongtai Zhang, Xiuming Zhang, Chu Han, Zaiyi Liu, Mingli Song, Anant Madabhushi, Cheng Lu","doi":"10.1007/s11263-026-02972-3","DOIUrl":"https://doi.org/10.1007/s11263-026-02972-3","url":null,"abstract":"","PeriodicalId":13752,"journal":{"name":"International Journal of Computer Vision","volume":"26 1","pages":""},"PeriodicalIF":19.5,"publicationDate":"2026-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148690890","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"ContextFusion and Bootstrap: An Effective Approach to Improve Slot Attention-Based Object-Centric Learning","authors":"Pinzhuo Tian, Shengjie Yang, Hang Yu, Alex C. Kot, Bihan Wen","doi":"10.1007/s11263-026-02964-3","DOIUrl":"https://doi.org/10.1007/s11263-026-02964-3","url":null,"abstract":"A key human ability is to decompose a scene into distinct objects and use their relationships to understand the environment. Object-centric learning aims to mimic this process in an unsupervised manner. Recently, the slot attention-based framework has emerged as a leading approach in this area and has been widely used in various downstream tasks. However, existing slot attention methods face two key limitations: (1) a lack of semantic information. In current methods, image areas are assigned to slots based on low-level features such as color and texture. This makes the model overly sensitive to low-level features and limits its understanding of object contours, shapes, or other semantic characteristics. (2) inability to fine-tune the encoder during training. Current methods require a stable feature space throughout training to enable reconstruction from slots, which restricts the flexibility needed for effective object-centric learning. To address these limitations, we propose a novel ContextFusion stage and a Bootstrap Branch, both of which can be seamlessly integrated into existing slot attention models. In the ContextFusion stage, we exploit semantic information from the foreground and background, incorporating an auxiliary indicator that provides additional contextual cues about them to enrich the semantic content beyond low-level features. In the Bootstrap Branch, we decouple feature adaptation from the original reconstruction phase and introduce a bootstrap strategy to train a feature-adaptive mechanism, allowing for more flexible adaptation. Experimental results show that our method significantly improves the performance of different SOTA slot attention models on both simulated and real-world datasets.","PeriodicalId":13752,"journal":{"name":"International Journal of Computer Vision","volume":"36 1","pages":""},"PeriodicalIF":19.5,"publicationDate":"2026-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148716151","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"GUIDED++: Enhancing Discrimination with Conjunctive Verification for Fine-Grained Open-Vocabulary Object Detection","authors":"Jiaming Li, Zhijia Liang, Shuangyin Liu, Chengpei Tang, Guanbin Li","doi":"10.1007/s11263-026-02986-x","DOIUrl":"https://doi.org/10.1007/s11263-026-02986-x","url":null,"abstract":"Fine-grained open-vocabulary detection (FG-OVD) challenges models to detect objects described by complex, compositional language. The prevalent strategy of encoding descriptive phrases into a single, holistic vector creates significant semantic ambiguity, hindering true compositional understanding. This ambiguity manifests as two opposing failures: attribute over-representation, where a visually dominant attribute leads to mislocalization, and attribute under-representation, where the model fails to enforce a conjunctive match across all specified attributes, leading to false positives. In this paper, we propose GUIDED++, a framework that systematically resolves both issues through a dual strategy. First, we employ architectural decoupling to separate coarse-grained localization from fine-grained discrimination, effectively mitigating attribute over-representation. Second, we introduce a novel conjunctive multi-attribute verification mechanism to explicitly combat attribute under-representation. This mechanism decomposes a complex query into its atomic attribute conditions, computes a distinct similarity score for each, and uses a minimal aggregation function to enforce a strict logical ‘AND’, ensuring an object satisfies all required attributes. Extensive experiments show that GUIDED++ significantly outperforms existing methods and establishes a new state-of-the-art on challenging FG-OVD benchmarks, demonstrating a more robust approach to compositional visual reasoning.","PeriodicalId":13752,"journal":{"name":"International Journal of Computer Vision","volume":"4 1","pages":""},"PeriodicalIF":19.5,"publicationDate":"2026-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148716159","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"ManiDream: Manifold Completion via Prototype-Anchored Dreaming for Long-Tailed Visual Recognition","authors":"Yuan Dong, Zhe Zhao, Liheng Yu, Di Wu, Pengkun Wang, Yang Wang","doi":"10.1007/s11263-026-02988-9","DOIUrl":"https://doi.org/10.1007/s11263-026-02988-9","url":null,"abstract":"","PeriodicalId":13752,"journal":{"name":"International Journal of Computer Vision","volume":"42 1","pages":""},"PeriodicalIF":19.5,"publicationDate":"2026-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148690888","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Mastering Regional 3DGS: Locating, Initializing, and Editing with Diverse 2D Priors","authors":"Lanqing Guo, Yufei Wang, Hezhen Hu, Yan Zheng, Yeying Jin, Siyu Huang, Zhangyang Wang","doi":"10.1007/s11263-026-02941-w","DOIUrl":"https://doi.org/10.1007/s11263-026-02941-w","url":null,"abstract":"Many 3D scene editing tasks focus on modifying local regions rather than the entire scene, except for some global applications like style transfer, and in the context of 3D Gaussian Splatting (3DGS), where scenes are represented by a series of Gaussians, this structure allows for precise regional edits, offering enhanced control over specific areas of the scene; however, the challenge lies in the fact that 3D semantic parsing often underperforms compared to its 2D counterpart, making targeted manipulations within 3D spaces more difficult and limiting the fidelity of edits, which we address by leveraging 2D diffusion editing to accurately identify modification regions in each view, followed by inverse rendering for 3D localization, then refining the frontal view and initializing a coarse 3DGS with consistent views and approximate shapes derived from depth maps predicted by a 2D foundation model, thereby supporting an iterative, view-consistent editing process that gradually enhances structural details and textures to ensure coherence across perspectives. Experiments demonstrate that our method achieves state-of-the-art performance while delivering up to a <inline-formula><alternatives><mml:math><mml:mrow><mml:mn>4</mml:mn><mml:mo>×</mml:mo></mml:mrow></mml:math><tex-math>documentclass[12pt]{minimal} usepackage{amsmath} usepackage{wasysym} usepackage{amsfonts} usepackage{amssymb} usepackage{amsbsy} usepackage{mathrsfs} usepackage{upgreek} setlength{oddsidemargin}{-69pt} begin{document}$$4times $$end{document}</tex-math></alternatives></inline-formula> speedup, providing a more efficient and effective approach to 3D scene local editing.","PeriodicalId":13752,"journal":{"name":"International Journal of Computer Vision","volume":"28 1","pages":""},"PeriodicalIF":19.5,"publicationDate":"2026-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148716152","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Scalable Image Restoration and Enhancement towards Diverse Downstream Applications","authors":"Juan Wang, Ke Zhang, Chunfeng Yuan, Congxuan Zhang, Bing Li, Weiming Hu, Stephen Maybank","doi":"10.1007/s11263-026-02957-2","DOIUrl":"https://doi.org/10.1007/s11263-026-02957-2","url":null,"abstract":"In the past decade, image restoration has witnessed a remarkable performance leap. However, existing methods still face two critical limitations: i) many methods train distortion-specific models, which struggle to address mixed distortions; ii) most methods employ reconstruction loss during training, with little consideration for the intended use of the restored images (e.g., human viewing, detection, or segmentation), leading to a mismatch between training objectives and application goals. In this paper, we propose a scalable framework for image restoration and enhancement built upon the reinforcement learning (RL) paradigm. At the core of our framework, the RL agent is capable of accurately perceiving distortion contexts and dynamically adjusting diverse restoration operators, which ensures our framework to effectively handle mixed-distortions, and generalize well to new tasks with minor additional cost. Furthermore, RL relaxes the differentiability constraints on optimization objectives, which enables our framework to directly optimize the restoration process toward application goals, thereby bridging the gap between training objectives and downstream demands. Extensive objective and subjective evaluations demonstrate that our method not only generates visually pleasing results for human perception but also significantly improves the performance of machine vision tasks such as detection and segmentation. We further validate the framework’s scalability through generalization evaluations on unseen distortions and multi-objective optimization experiments. The results confirm the model’s superior few-shot and zero-shot capabilities compared to existing methods, as well as its flexibility in addressing multiple competing objectives. Finally, comprehensive ablation studies and hyperparameter analyses provide valuable insights into the design choices and behavior of our framework.","PeriodicalId":13752,"journal":{"name":"International Journal of Computer Vision","volume":"9 1","pages":""},"PeriodicalIF":19.5,"publicationDate":"2026-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148688033","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Multimodal Domain Generalization via Adaptive Dual-Objective Feature Learning","authors":"Hongzhao Li, Siwei Liu, Guohao Shen, Shupan Li, Mingliang Xu","doi":"10.1007/s11263-026-02991-0","DOIUrl":"https://doi.org/10.1007/s11263-026-02991-0","url":null,"abstract":"Recent years have witnessed the widespread adoption of multimodal applications across various real-world scenarios. However, these applications often face significant challenges due to distribution shifts across different domains, which can severely impact model performance and reliability. While domain generalization has been extensively studied for unimodal scenarios, its multimodal counterpart remains underexplored, presenting unique challenges in addressing both modality heterogeneity and domain shifts simultaneously. We argue that an effective multimodal domain generalization framework should not only learn domain invariance but also balance the invariance and specificity of modalities. To bridge this gap, we introduce Adaptive Dual-Objective Feature Learning for Multimodal Domain Generalization (ADMMDG), a framework that separates feature learning into two complementary components: features that capture shared patterns with both modality and domain invariance, and modality specific features that preserve the unique characteristics of each modality while maintaining domain invariance. To achieve this, ADMMDG employs two distinct contrastive learning strategies that focus on aligning features across different domains and modalities. Both strategies are equipped with a dynamic weighting mechanism that assigns higher weights to modal-domain feature pairs exhibiting greater modality or domain discrepancies, thereby effectively capturing the respective feature learning objectives. Extensive experiments on multiple benchmark datasets, utilizing diverse modality combinations, demonstrate the effectiveness of ADMMDG in both multi-source and single-source multimodal domain generalization tasks, as well as in the challenging multimodal open-set domain generalization scenario. Our codes are available at <ext-link ext-link-type=\"uri\" xlink:href=\"https://github.com/lihongzhao99/ADMMDG\">https://github.com/lihongzhao99/ADMMDG</ext-link>.","PeriodicalId":13752,"journal":{"name":"International Journal of Computer Vision","volume":"12 1","pages":""},"PeriodicalIF":19.5,"publicationDate":"2026-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148716158","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"MUG: Multi-human Graph Network for 3D Mesh Reconstruction from 2D Pose","authors":"Chenyan Wu, Yandong Li, Xianfeng Tang, Zhe Huang, James Z. Wang","doi":"10.1007/s11263-026-02942-9","DOIUrl":"https://doi.org/10.1007/s11263-026-02942-9","url":null,"abstract":"Reconstructing multi-human body meshes from a single monocular image is a crucial yet challenging problem in computer vision. This problem requires not only generating individual body mesh models for each person but also estimating the relative 3D positions among subjects to produce a coherent scene representation. In this work, we introduce MUG (Multi-hUman Graph network), which employs a single graph neural network to construct coherent multi-human meshes using only 2D pose data as input. Our approach demonstrates that purely pose-based methods can effectively perform simultaneous depth reasoning and multi-human mesh generation. Existing image-based methods typically rely on lab-collected training datasets with accurate 3D labels; however, these datasets often introduce an image domain gap when applied to in-the-wild testing data or art images due to differences in appearance and context. In contrast, MUG leverages the geometric consistency of 2D poses across diverse datasets, mitigating domain discrepancies. The MUG network operates in three primary phases. Initially, to model the multi-human environment, it processes multi-human 2D poses and constructs a novel heterogeneous graph. This graph connects nodes both across different people and within individuals to capture inter-human interactions and accurately represent body geometry, including skeletal and mesh structures. Subsequently, it employs a dual-branch graph neural network: one branch predicts inter-human depth relations, while the other predicts the root-joint-relative mesh coordinates. Finally, the complete multi-human 3D meshes are constructed by combining the outputs from both branches. Despite the simplicity of using only 2D pose inputs and streamlined network architecture, MUG outperforms existing multi-human mesh estimation methods. This superiority is consistently observed across various datasets from diverse domains, such as RH, MuPoTS-3D, and 3DPW. Qualitative results show that MUG can effectively handle art images, through-wall scenarios, and poor lighting conditions when incorporating advanced 2D pose networks. Both qualitative and quantitative evaluations highlight MUG’s remarkable generalization ability in open-world scenarios.","PeriodicalId":13752,"journal":{"name":"International Journal of Computer Vision","volume":"26 1","pages":""},"PeriodicalIF":19.5,"publicationDate":"2026-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148687812","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"SaLon3R: Structure-Aware Long-Term Feedforward 3D Reconstruction from Unposed Images","authors":"Jiaxin Guo, Tongfan Guan, Wenzhen Dong, Wenzhao Zheng, Wenting Wang, Yue Wang, Yeung Yam, Yun-Hui Liu","doi":"10.1007/s11263-026-02965-2","DOIUrl":"https://doi.org/10.1007/s11263-026-02965-2","url":null,"abstract":"Recent advances in 3D Gaussian Splatting (3DGS) have enabled feed-forward, on-the-fly reconstruction of sequential input views. However, existing methods often predict per-pixel Gaussians and combine Gaussians from all views as the scene representation, leading to substantial redundancies and geometric inconsistencies in long-duration video sequences. To address this, we propose <bold>SaLon3R</bold>, a novel framework for <bold>S</bold>tructure-<bold>a</bold>ware, <bold>Lon</bold>g-term <bold>3</bold>DGS <bold>R</bold>econstruction. Our method eliminates redundancy by introducing compact anchor primitives as a replacement for per-pixel Gaussians. These primitives are derived through a differentiable, saliency-aware Gaussian quantization process designed to preserve fidelity while ensuring a compact representation. Specifically, a foundational 3D reconstruction model is employed to predict a saliency map encoding regional geometric complexity. Guided by this saliency map, we compress redundant Gaussian primitives into compact anchors by prioritizing high-complexity regions. Furthermore, we introduce a 3D Point Transformer to overcome geometric inconsistencies caused by long-term accumulative errors. It refines attributes and saliency of the anchor primitives leveraging the learned spatial structural priors in 3D space. Without known camera parameters or test-time optimization, our approach effectively prunes the redundant 3DGS and resolves artifacts in a single feed-forward pass. Experiments on multiple datasets demonstrate our approach outperform state-of-the-arts on both novel view synthesis and depth estimation, while exhibiting superior efficiency (<inline-formula><alternatives><mml:math><mml:mrow><mml:mo>&gt;</mml:mo><mml:mspace width=\"-0.166667em\"></mml:mspace></mml:mrow></mml:math><tex-math>documentclass[12pt]{minimal} usepackage{amsmath} usepackage{wasysym} usepackage{amsfonts} usepackage{amssymb} usepackage{amsbsy} usepackage{mathrsfs} usepackage{upgreek} setlength{oddsidemargin}{-69pt} begin{document}$$&gt;!$$end{document}</tex-math></alternatives></inline-formula><bold>10</bold><monospace>FPS</monospace>), robustness, and generalization ability for long-term feed-forward Gaussian reconstruction.","PeriodicalId":13752,"journal":{"name":"International Journal of Computer Vision","volume":"382 1","pages":""},"PeriodicalIF":19.5,"publicationDate":"2026-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148687994","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Adapting Vision-Language Models Without Labels: A Comprehensive Survey","authors":"Hao Dong, Lijun Sheng, Jian Liang, Ran He, Eleni Chatzi, Olga Fink","doi":"10.1007/s11263-026-02987-w","DOIUrl":"https://doi.org/10.1007/s11263-026-02987-w","url":null,"abstract":"","PeriodicalId":13752,"journal":{"name":"International Journal of Computer Vision","volume":"358 1","pages":""},"PeriodicalIF":19.5,"publicationDate":"2026-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148690889","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}