International Journal of Computer Vision最新文献

{"title":"Multimodal Referring Segmentation: A Survey","authors":"Henghui Ding, Song Tang, Shuting He, Chang Liu, Zuxuan Wu, Yu-Gang Jiang","doi":"10.1007/s11263-026-02943-8","DOIUrl":"https://doi.org/10.1007/s11263-026-02943-8","url":null,"abstract":"","PeriodicalId":13752,"journal":{"name":"International Journal of Computer Vision","volume":"27 1","pages":""},"PeriodicalIF":19.5,"publicationDate":"2026-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148842886","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":"P-PatchDiff: Progressive Patch Diffusion Models for Low-Light Image Enhancement","authors":"Ruoyu Guo, Haonan Zhong, Maurice Pagnucco, Yang Song","doi":"10.1007/s11263-026-02995-w","DOIUrl":"https://doi.org/10.1007/s11263-026-02995-w","url":null,"abstract":"Recent advancements in low-light image enhancement have leveraged diffusion models for their strong ability to generate perceptually realistic, detailed images. Patch diffusion models further offer a promising solution to size-agnostic image restoration while improving efficiency. However, existing methods typically rely on small, fixed patches (e.g., 64 <jats:inline-formula> <jats:alternatives> <jats:tex-math>$$times $$</jats:tex-math> <mml:math xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"> <mml:mo>×</mml:mo> </mml:math> </jats:alternatives> </jats:inline-formula> 64) that cannot capture image-level brightness context, whereas enlarging the receptive field improves brightness and colour estimation but substantially increases computational cost. Moreover, low-light images often exhibit uneven brightness across regions, making it necessary to ensure that locally enhanced patches remain visually coherent when combined into the full image. To address these limitations, we propose P-PatchDiff, a scalable progressive patch diffusion framework for low-light image enhancement that dynamically adjusts patch size throughout the denoising process, enabling a gradual shift from local to global views. A Multi-Patch Alignment strategy is also introduced to normalise features across varying patch scales using an estimated global brightness proxy. Rather than pursuing pixel-level reconstruction accuracy, P-PatchDiff focuses on scalability and coherent brightness across the whole image, allowing the model to perceive multi-scale information and better enhance regions with varying brightness. We empirically demonstrate that P-PatchDiff effectively enhances images ranging from 400 <jats:inline-formula> <jats:alternatives> <jats:tex-math>$$times $$</jats:tex-math> <mml:math xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"> <mml:mo>×</mml:mo> </mml:math> </jats:alternatives> </jats:inline-formula> 600 to 4K and is 80 <jats:inline-formula> <jats:alternatives> <jats:tex-math>$$times $$</jats:tex-math> <mml:math xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"> <mml:mo>×</mml:mo> </mml:math> </jats:alternatives> </jats:inline-formula> faster than existing patch diffusion models while using less than 9GB of memory. The code is available at <jats:ext-link xmlns:xlink=\"http://www.w3.org/1999/xlink\" xlink:href=\"https://github.com/RuoyuGuo/P-PatchDiff\" ext-link-type=\"uri\">https://github.com/RuoyuGuo/P-PatchDiff</jats:ext-link> .","PeriodicalId":13752,"journal":{"name":"International Journal of Computer Vision","volume":"348 1","pages":""},"PeriodicalIF":19.5,"publicationDate":"2026-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148769011","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":"TEPR: Thermal Edge-Prompted Geometry Learning for Multi-View 3D Reconstruction","authors":"Zhiheng Li, Zuntao Liu, Weihua Wang, Zheng Fang","doi":"10.1007/s11263-026-02997-8","DOIUrl":"https://doi.org/10.1007/s11263-026-02997-8","url":null,"abstract":"","PeriodicalId":13752,"journal":{"name":"International Journal of Computer Vision","volume":"9 1","pages":""},"PeriodicalIF":19.5,"publicationDate":"2026-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148769013","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":"AvatarShield: Visual Reinforcement Learning for Human-Centric Synthetic Video Detection","authors":"Zhipei Xu, Xuanyu Zhang, Qing Huang, Xing Zhou, Jian Zhang","doi":"10.1007/s11263-026-02954-5","DOIUrl":"https://doi.org/10.1007/s11263-026-02954-5","url":null,"abstract":"","PeriodicalId":13752,"journal":{"name":"International Journal of Computer Vision","volume":"31 1","pages":""},"PeriodicalIF":19.5,"publicationDate":"2026-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148769012","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":"Query-Free Black-Box Universal Adversarial Attacks on Gait Recognition","authors":"Saihui Hou, Chenye Wang, Hui Su, Yongzhen Huang","doi":"10.1007/s11263-026-02982-1","DOIUrl":"https://doi.org/10.1007/s11263-026-02982-1","url":null,"abstract":"","PeriodicalId":13752,"journal":{"name":"International Journal of Computer Vision","volume":"34 1","pages":""},"PeriodicalIF":19.5,"publicationDate":"2026-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148769014","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":"RoFLIP: Robust and Fine-Grained Alignment for Vision-Language Compositional Reasoning","authors":"Yiwei Sun, Chuanbin Liu, Shancheng Fang, Pandeng Li, Zhiying Lu, Hongtao Xie","doi":"10.1007/s11263-026-02944-7","DOIUrl":"https://doi.org/10.1007/s11263-026-02944-7","url":null,"abstract":"","PeriodicalId":13752,"journal":{"name":"International Journal of Computer Vision","volume":"17 1","pages":""},"PeriodicalIF":19.5,"publicationDate":"2026-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148769056","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":"LatentFlow3D: Unified Point Cloud Processing via Latent Space Modeling in Invertible Neural Networks","authors":"Aihua Mao, Biao Yan, Jun Yang, Yaqi Duan, Ran Yi, Yong-Jin Liu, Ying He","doi":"10.1007/s11263-026-02990-1","DOIUrl":"https://doi.org/10.1007/s11263-026-02990-1","url":null,"abstract":"","PeriodicalId":13752,"journal":{"name":"International Journal of Computer Vision","volume":"20 1","pages":""},"PeriodicalIF":19.5,"publicationDate":"2026-08-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148728761","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":"Single Domain Generalization Benchmark: Current State and Challenges","authors":"Kavindya Imbulgoda, Ruwan Tennakoon, Wei Quin Chuah, Steven Korevaar, Feng Xia, Alireza Bab-Hadiashar","doi":"10.1007/s11263-026-02985-y","DOIUrl":"https://doi.org/10.1007/s11263-026-02985-y","url":null,"abstract":"Recent advances in deep learning have enabled remarkable success across computer vision tasks using massive datasets, yet the persistent challenge of domain shift-where training and testing distributions differ-continues to degrade model performance. While Domain Generalization techniques aim to learn invariant representations across multiple domains, their reliance on diverse training domains limits applicability in settings where multiple source domains are not available. This survey examines Single Domain Generalization (SDG) approaches that leverage targeted inductive biases to enhance out-of-domain (OOD) performance using a single source domain, addressing key questions regarding their effectiveness across various domain shifts, different model architectures such as CNNs and Vision transformers, and the impact of shape bias for OOD generalization. These questions are crucial as they directly inform the development of robust models that can reliably operate under real-world conditions, guiding the research community in overcoming limitations of current techniques. Our findings indicate that although SDG methods improve performance under highly domain distinguishable stylized shifts, they exhibit limited robustness to background, correlation and corruption shifts on larger datasets, and increased shape bias does not consistently yield enhanced OOD performance, thereby underscoring the need for further research into developing more resilient and generalizable models. For reproducibility, the implementation and code used in our benchmark are available on our official <jats:ext-link xmlns:xlink=\"http://www.w3.org/1999/xlink\" xlink:href=\"https://github.com/Kavindya98/SDG-Benchmark\" ext-link-type=\"uri\">https://github.com/Kavindya98/SDG-Benchmark</jats:ext-link> GitHub repository.","PeriodicalId":13752,"journal":{"name":"International Journal of Computer Vision","volume":"27 1","pages":""},"PeriodicalIF":19.5,"publicationDate":"2026-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148728764","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":"SCALAR++: Efficient Controllable Generation via Scale-wise Visual Autoregressive Learning","authors":"Ryan Xu, Dongyang Jin, Shawn Chen, Yancheng Bai, Jingzhe Ma, Rui Lan, Jianhao Zeng, Yunyang Ge, Mingzhe Zheng, Lei Sun, Xiangxiang Chu","doi":"10.1007/s11263-026-02984-z","DOIUrl":"https://doi.org/10.1007/s11263-026-02984-z","url":null,"abstract":"","PeriodicalId":13752,"journal":{"name":"International Journal of Computer Vision","volume":"49 1","pages":""},"PeriodicalIF":19.5,"publicationDate":"2026-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148728762","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":"Long Story Short: Story-level Video Understanding from 20K Short Films","authors":"Ridouane Ghermi, Xi Wang, Vicky Kalogeiton, Ivan Laptev","doi":"10.1007/s11263-026-02940-x","DOIUrl":"https://doi.org/10.1007/s11263-026-02940-x","url":null,"abstract":"","PeriodicalId":13752,"journal":{"name":"International Journal of Computer Vision","volume":"130 1","pages":""},"PeriodicalIF":19.5,"publicationDate":"2026-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148728763","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}