International Journal of Computer Vision最新文献_第7页

MotionStruct4D: Discovering Motion Structure of Gaussian Splatting for Video-to-4D Generation MotionStruct4D：发现视频到4d生成的高斯飞溅运动结构

IF 19.5 2区计算机科学

International Journal of Computer Vision Pub Date : 2026-09-02 DOI: 10.1007/s11263-026-02992-z

Jia-Xing Zhong, Kai Lu, Jiaojiao Ye, Niki Trigoni, Andrew Markham

{"title":"MotionStruct4D: Discovering Motion Structure of Gaussian Splatting for Video-to-4D Generation","authors":"Jia-Xing Zhong, Kai Lu, Jiaojiao Ye, Niki Trigoni, Andrew Markham","doi":"10.1007/s11263-026-02992-z","DOIUrl":"https://doi.org/10.1007/s11263-026-02992-z","url":null,"abstract":"Monocular Video-to-4D generation faces the fundamental challenge of inferring plausible 3D geometry and motion from limited single-view inputs. We present MotionStruct4D, a novel approach that discovers and exploits the underlying motion structure of 3D Gaussian Splatting for high-quality video-to-4D generation. Our key insight is that real-world motion can be effectively decomposed into coarse rigid transformations that capture principal movements, complemented by detailed non-rigid deformations that account for fine-grained details. MotionStruct4D introduces: (1) a self-supervised motion structure discovery module that identifies quasi-rigid parts by preserving spatiotemporal relationships without explicit 3D supervision, and (2) a weighted dense-to-sparse optimization architecture that transitions from dense per-Gaussian deformation to sparse control points, effectively integrating rigid and non-rigid motion components through adaptive weighted fusion. This design addresses the parametric imbalance between rigid and non-rigid motions and effectively models 3D movements across different kinematic patterns. To evaluate our approach on challenging scenarios, we curate a comprehensive benchmark dataset featuring substantial object displacement and diverse articulated motion patterns. Experimental results demonstrate MotionStruct4D’s superior performance in motion fidelity and novel viewpoint synthesis quality, while also providing interpretable motion structure decomposition that reveals meaningful quasi-rigid part segmentation.","PeriodicalId":13752,"journal":{"name":"International Journal of Computer Vision","volume":"43 1","pages":""},"PeriodicalIF":19.5,"publicationDate":"2026-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148884075","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}

引用次数: 0

Two-Stage Multi-Modal Fusion with Adaptive Alignment for Action Quality Assessment 基于自适应对齐的两阶段多模态融合行动质量评估

IF 19.5 2区计算机科学

International Journal of Computer Vision Pub Date : 2026-09-02 DOI: 10.1007/s11263-026-02960-7

Kanglei Zhou, Ruizhi Cai, Xinning Wang, Yijian Zheng, Liyuan Wang, Jianguo Li, Xiaohui Liang

引用次数: 0

Disco4D: Towards Prior-Free Motion Representation Learning for Point Cloud Videos Via Self-Disentangled Contrastive Pre-Training 通过自解纠缠对比预训练实现点云视频的无先验运动表示学习

IF 19.5 2区计算机科学

International Journal of Computer Vision Pub Date : 2026-09-01 DOI: 10.1007/s11263-026-03008-6

Zhi Zuo,Chenyi Zhuang,Pan Gao,Jie Qin,Hao Feng,Nicu Sebe

引用次数: 0

Semantic Invariant Representation Learning and Data-Driven Label Prototype Modeling for Incomplete Multi-view Multi-label Classification 不完全多视图多标签分类的语义不变表示学习和数据驱动标签原型建模

IF 19.5 2区计算机科学

International Journal of Computer Vision Pub Date : 2026-09-01 DOI: 10.1007/s11263-026-03025-5

Chengliang Liu,Bo Li,Jie Wen,Yong Xu,Wenqi Ren,Xiaochun Cao,Chao Huang

引用次数: 0

MonoSOWA++: Universal Autolabeling Pipeline for Monocular 3D Object Detection monosowa++：用于单目3D物体检测的通用自动标记管道

IF 19.5 2区计算机科学

International Journal of Computer Vision Pub Date : 2026-09-01 DOI: 10.1007/s11263-026-03007-7

Jan Skvrna,Lukas Neumann

引用次数: 0

ShapeRhythm: Personalized and Harmonic Dance Generation Bridging Diverse Bodies and Melodies shaperhym：跨越形体与旋律的个性化和谐舞蹈

IF 19.5 2区计算机科学

International Journal of Computer Vision Pub Date : 2026-09-01 DOI: 10.1007/s11263-026-03017-5

Muyi Sun,Zezhao Tian,Xingqun Qi,Chen Su,Xurui Hu,Qifeng Liu,Man Zhang,Zhenan Sun,Caifeng Shan

{"title":"ShapeRhythm: Personalized and Harmonic Dance Generation Bridging Diverse Bodies and Melodies","authors":"Muyi Sun,Zezhao Tian,Xingqun Qi,Chen Su,Xurui Hu,Qifeng Liu,Man Zhang,Zhenan Sun,Caifeng Shan","doi":"10.1007/s11263-026-03017-5","DOIUrl":"https://doi.org/10.1007/s11263-026-03017-5","url":null,"abstract":"Abstract Deriving vivid and expressive 3D human dance from music signals has gained tremendous progress in virtual avatar animation. Existing approaches typically overlook the diversity of human body shapes and generate dance motions using standardized body representations, without explicitly modeling the intrinsic relationship between body shape variations (i.e., thinness or plumpness) and musical rhythm. As a result, the synthesized dance motion lacks both personalization and harmony. Moreover, the absence of high-quality human dance datasets, particularly those incorporating bodyshape variations and annotations, also poses a significant challenge for this problem. To address this issue, we first newly compile a large-scale 3D human dance dataset, named ShapeDancer , which encompasses 13,574 s of data paired with detailed body shape variations. Additionally, we propose ShapeRhythm , a novel framework that allows personalized and harmonic dance generation, bridging diverse human bodies with expressive melodies. Our ShapeRhythm framework is built upon unifying the music signals and shape-aware text descriptions as conditions. Specifically, to enhance the dance personalization, we propose FreeShape , a delicate shape similarity matching approach which realizes freestyle and open-vocabulary text-guided bodyshape conversion. Furthermore, we design FreeDance to diversify and harmonize the dance motion generation, while preserving the shape-aware temporal consistency with music rhythm. Meanwhile, a fine-grained physics-guided Foot-Ground Interaction Constraint (FGI) is introduced to alleviate foot-skating artifacts and enhance detailed foot rhythm coordination. Extensive experiments conducted on our newly collected ShapeDancer dataset demonstrate that ShapeRhythm achieves state-of-the-art performance, realizing personalized and harmonic dance generation. More details are available on our project page .","PeriodicalId":13752,"journal":{"name":"International Journal of Computer Vision","volume":"31 14 1","pages":""},"PeriodicalIF":19.5,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148932874","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}

引用次数: 0

Generalized Logit Adjustment: Improved Fine-tuning by Mitigating Label Bias in Zero-Shot Vision Models 广义Logit调整：通过减轻零射击视觉模型中的标签偏差来改进微调

IF 19.5 2区计算机科学

International Journal of Computer Vision Pub Date : 2026-09-01 DOI: 10.1007/s11263-026-03012-w

Beier Zhu,Qianru Sun,Xun Yang,Hanwang Zhang

引用次数: 0

OV-EvDet: Event-Based Open-Vocabulary Object Detection OV-EvDet：基于事件的开放词汇对象检测

IF 19.5 2区计算机科学

International Journal of Computer Vision Pub Date : 2026-09-01 DOI: 10.1007/s11263-026-03014-8

Siqi Li,Shouan Pan,Wei Bao,Yongji Zhang,Haoning Xi,Zongze Wu,Yue Gao

引用次数: 0

MLA-Trust: Benchmarking Trustworthiness of Multimodal LLM Agents in GUI Environments MLA-Trust: GUI环境中多模态LLM代理可信度的基准测试