{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T06:04:50Z","timestamp":1784268290233,"version":"3.55.0"},"reference-count":77,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key R&D Program of China","doi-asserted-by":"publisher","award":["2024YFB2809105"],"award-info":[{"award-number":["2024YFB2809105"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["U24B20154,62172364"],"award-info":[{"award-number":["U24B20154,62172364"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01028","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"11047-11057","source":"Crossref","is-referenced-by-count":2,"title":["Diffuman4D: 4D Consistent Human View Synthesis From Sparse-View Videos With Spatio-Temporal Diffusion Models"],"prefix":"10.1109","author":[{"given":"Yudong","family":"Jin","sequence":"first","affiliation":[{"name":"Zhejiang University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sida","family":"Peng","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuan","family":"Wang","sequence":"additional","affiliation":[{"name":"Ant Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tao","family":"Xie","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhen","family":"Xu","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yifan","family":"Yang","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yujun","family":"Shen","sequence":"additional","affiliation":[{"name":"Ant Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hujun","family":"Bao","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaowei","family":"Zhou","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Github","year":"2021"},{"issue":"5","key":"ref2","first-page":"12","article-title":"Creation of 3d human avatar using kinect","volume":"1","author":"Aitpayev","year":"2012","journal-title":"Asian Transactions on Fundamentals of Electronics, Communication & Multimedia"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72952-2_4"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00764"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.265"},{"key":"ref6","first-page":"1","volume":"3","author":"Brooks","year":"2024","journal-title":"Video generation models as world simulators."},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00021"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01840"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72664-4_21"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.01829"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/2766945"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657463"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3550469.3555383"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01201"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.106"},{"key":"ref16","article-title":"Cat3d: Create anything in 3d with multi-view diffusion models","author":"Gao","year":"2024","journal-title":"NeurIPS 2024"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1117\/12.509898"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00482"},{"key":"ref19","article-title":"Cogvideo: Large-scale pretraining for text-to-video generation via transformers","author":"Hong","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01930"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3592415"},{"key":"ref22","article-title":"Pl\u00fccker coordinates for lines in the space","volume":"3","author":"Jia","year":"2020","journal-title":"Problem Solver Techniques for Applied Computer Science, Com-S-477\/577 Course Handout"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/93.580394"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73235-5_12"},{"key":"ref26","article-title":"Hunyuanvideo: A systematic framework for large video generative models","author":"Kong","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref27","first-page":"62189","article-title":"Vivid-zoo: Multi-view video generation with diffusion model","volume":"37","author":"Li","year":"2025","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00544"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01864"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3550469.3555376"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/3DV53792.2021.00032"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00853"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72649-1_3"},{"key":"ref34","article-title":"Syncdreamer: Generating multiview-consistent images from a single-view image","author":"Liu","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3596711.3596800"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298631"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-025-02615-z"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00581"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3478513.3480487"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01405"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00894"},{"key":"ref43","article-title":"Dreamfusion: Text-to-3d using 2d diffusion","author":"Poole","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01018"},{"key":"ref45","article-title":"Dreamgaussian4d: Generative 4d gaussian splatting","author":"Ren","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.445"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_31"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01596"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1002\/cav.1579"},{"key":"ref50","article-title":"Mvdream: Multi-view diffusion for 3d generation","author":"Shi","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref51","article-title":"Text-to-4d dynamic scene generation","author":"Singer","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1016\/j.gmod.2005.01.008"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/MCG.2007.68"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2012.56"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01316"},{"key":"ref56","article-title":"Imagedream: Image-prompt multi-view diffusion for 3d generation","author":"Wang","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref57","article-title":"Controlling space and time with diffusion models","author":"Watson","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01573"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01920"},{"key":"ref60","article-title":"Cat4d: Create anything in 4 d with multi-view video diffusion models","author":"Wu","year":"2024","journal-title":"arXiv"},{"key":"ref61","article-title":"Sv4d: Dynamic 3d content generation with multi-frame and multi-view consistency","author":"Xie","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/3610543.3626173"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00100"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01893"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/3687919"},{"key":"ref66","first-page":"arXiv2404","article-title":"Diffusion2: Dynamic 3d content generation via score composition of orthogonal diffusion models","author":"Yang","year":"2024","journal-title":"arXiv e-prints"},{"key":"ref67","article-title":"Cogvideox: Text-to-video diffusion models with an expert transformer","author":"Yang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref68","article-title":"Realtime photorealistic dynamic scene representation and rendering with 4 d gaussian splatting","volume-title":"International Conference on Learning Representations (ICLR)","author":"Yang"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_47"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00567"},{"key":"ref71","article-title":"4dgen: Grounded 4d content generation with spatial-temporal consistency","author":"Yin","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72764-1_10"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0488"},{"key":"ref74","article-title":"Cameras as rays: Pose estimation via ray diffusion","author":"Zhang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref75","article-title":"Animate124: Animating one image to 4d dynamic scene","author":"Zhao","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01861"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00697"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11445759.pdf?arnumber=11445759","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:46:47Z","timestamp":1777531607000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445759\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":77,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01028","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}