{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,29]],"date-time":"2026-10-29T23:13:57Z","timestamp":1793315637106,"version":"4.5.0"},"reference-count":53,"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62206244"],"award-info":[{"award-number":["62206244"]}],"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\/iccv51701.2025.00538","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"5680-5689","source":"Crossref","is-referenced-by-count":10,"title":["POMATO: Marrying Pointmap Matching with Temporal Motions for Dynamic 3D Reconstruction"],"prefix":"10.1109","author":[{"given":"Songyan","family":"Zhang","sequence":"first","affiliation":[{"name":"Nanyang Technological University,Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongtao","family":"Ge","sequence":"additional","affiliation":[{"name":"Zhejiang University,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinyuan","family":"Tian","sequence":"additional","affiliation":[{"name":"Zhejiang University,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guangkai","family":"Xu","sequence":"additional","affiliation":[{"name":"Zhejiang University,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Chen","sequence":"additional","affiliation":[{"name":"Zhejiang University,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chen","family":"Lv","sequence":"additional","affiliation":[{"name":"Nanyang Technological University,Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chunhua","family":"Shen","sequence":"additional","affiliation":[{"name":"Zhejiang University,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Affineglue: Joint matching and robust estimation","author":"Barath","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","volume-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","volume":"abs\/2311.15127","author":"Blattmann","year":"2023"},{"key":"ref3","author":"Bochkovskii","year":"2024","journal-title":"Depth pro: Sharp monocular metric depth in less than a second"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33783-3_44"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00021"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02126"},{"key":"ref7","article-title":"Bundle adjustment revisited","author":"Chen","year":"2019","journal-title":"arXiv preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00060"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00923"},{"key":"ref10","first-page":"1","article-title":"Carla: An open urban driving simulator","volume-title":"Conference on robot learning","author":"Dosovitskiy","year":"2017"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72670-5_14"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1561\/0600000052"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref14","volume-title":"Animatediff: Animate your personalized text-toimage diffusion models without specific tuning","author":"Guo","year":"2023"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_4"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3444912"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00193"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3592415"},{"key":"ref19","article-title":"Neural fields in robotics: A survey","author":"Irshad","year":"2024","journal-title":"arXiv preprint"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2782743"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01271"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73033-7_2"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00907"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"ref25","article-title":"Tapvid-3d: A benchmark for tracking any point in 3d","author":"Koppula","year":"2024","journal-title":"arXiv preprint"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73220-1_5"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01616"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"ref29","article-title":"DINOv2: Learning robust visual features without supervision","author":"Oquab","year":"2024","journal-title":"Trans. Mach. Learn. Research"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967590"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01842"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.440"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01196"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10584-0_38"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-008-0136-6"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02127"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6385773"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_24"},{"key":"ref39","article-title":"Droid-slam: Deep visual slam for monocular, stereo, and rgb-d cameras","author":"Teed","year":"2021","journal-title":"Neural Information Processing Systems"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72691-0_18"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/3dv66043.2025.00013"},{"key":"ref42","article-title":"Shape of motion: 4 d reconstruction from a single video","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00983"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01956"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341801"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01929"},{"key":"ref47","article-title":"Diffusion models trained with large data are transferable visual models","author":"Xu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref48","article-title":"Dg-slam: Robust dynamic gaussian splatting slam with hybrid pose optimization","author":"Xu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref49","article-title":"Depth any video with scalable synthetic data","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0688"},{"key":"ref51","article-title":"Monst3r: A simple approach for estimating geometry in the presence of motion","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01122"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01818"}],"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\/11444728.pdf?arnumber=11444728","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:07:14Z","timestamp":1777612034000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444728\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00538","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}