{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T09:28:32Z","timestamp":1780392512527,"version":"3.54.1"},"reference-count":96,"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\/501100020707","name":"Information Technology Center","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100020707","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100011442","name":"State Key Lab of CAD&CG","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100011442","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004835","name":"Zhejiang University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004835","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\/iccv51701.2025.00633","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"6726-6737","source":"Crossref","is-referenced-by-count":2,"title":["SpatialTrackerV2: Advancing 3D Point Tracking with Explicit Camera Motion"],"prefix":"10.1109","author":[{"given":"Yuxi","family":"Xiao","sequence":"first","affiliation":[{"name":"Zhejiang University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianyuan","family":"Wang","sequence":"additional","affiliation":[{"name":"Oxford"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nan","family":"Xue","sequence":"additional","affiliation":[{"name":"Ant Group"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nikita","family":"Karaev","sequence":"additional","affiliation":[{"name":"Oxford"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuri","family":"Makarov","sequence":"additional","affiliation":[{"name":"Pixelwise AI"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bingyi","family":"Kang","sequence":"additional","affiliation":[{"name":"Bytedance Seed"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xing","family":"Zhu","sequence":"additional","affiliation":[{"name":"Ant Group"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hujun","family":"Bao","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yujun","family":"Shen","sequence":"additional","affiliation":[{"name":"Ant Group"}],"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","article-title":"L4p: Low-level 4d vision perception unified","author":"Badki","year":"2025","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2007.09.014"},{"key":"ref3","article-title":"Zoedepth: Zero-shot transfer by combining relative and metric depth","author":"Farooq Bhat","year":"2023","journal-title":"arXiv preprint"},{"key":"ref4","article-title":"Gs-dit: Advancing video generation with pseudo 4d gaussian fields through efficient dense 3d point tracking","author":"Bian","year":"2025","journal-title":"CoRR, abs\/2501.02690"},{"key":"ref5","article-title":"Midas v3.1 A model zoo for robust monocular relative depth estimation","author":"Birkl","year":"2023","journal-title":"CoRR, abs\/2307.14460"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00843"},{"key":"ref7","author":"Cabon","journal-title":"Virtual kitti 2, 2020"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02126"},{"key":"ref10","article-title":"Pref3r: Posefree feed-forward 3d gaussian splatting from variable-length image sequence","author":"Chen","year":"2024","journal-title":"C o R R, abs\/2411.16877"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72684-2_18"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref13","first-page":"8780","article-title":"Diffusion models beat gans on image synthesis","volume-title":"Advances in Neural Information Processing Systems","volume":"34","author":"Dhariwal","year":"2021"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0989"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00923"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-96-0901-7_28"},{"key":"ref17","first-page":"2366","article-title":"Depth map prediction from a single image using a multi-scale deep network","author":"Eigen","year":"2014","journal-title":"NeurIPS"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00214"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913491297"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01842"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00373"},{"key":"ref22","article-title":"Diffusion as shader: 3daware video diffusion for versatile video generation control","author":"Gu","year":"2025","journal-title":"CoRR, abs\/2501.03847"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_4"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511811685"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/34.601246"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3444912"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00193"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00298"},{"key":"ref29","author":"Jeong","year":"2024","journal-title":"Track4gen: Teaching video diffusion models to track points improves video generation. CoRR, abs\/2412.06016"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00982"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01271"},{"key":"ref32","article-title":"Cotracker3: Simpler and better point tracking by pseudolabelling real videos","author":"Karaev","year":"2024","journal-title":"arXiv preprint"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73033-7_2"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3047"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.169"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00166"},{"key":"ref37","article-title":"Tapvid-3d: A benchmark for tracking any point in 3d","author":"Koppula","year":"2024","journal-title":"NeurIPS"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00578"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2006.579"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72640-8_4"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2537"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00981"},{"key":"ref43","author":"Lin","year":"2023","journal-title":"Relpose++: Recovering 6d poses from sparse-view observations. arXiv preprint"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02092"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.147"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02034"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/2816795.2818013"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/icra55743.2025.11128786"},{"key":"ref49","article-title":"Object Recognition from Local ScaleInvariant Features","volume-title":"Proc. ICCV","author":"Lowe","year":"1999"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000029664.99615.94"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01546"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.438"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00482"},{"key":"ref54","article-title":"Delta: Dense efficient long-range 3d tracking for any video","author":"Duc Ngo","year":"2024","journal-title":"arXiv preprint"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2004.17"},{"key":"ref56","article-title":"Pretraining auto-regressive robotic models with 4d representations","author":"Niu","year":"2025","journal-title":"arXiv preprint"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00773"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1017\/S096249291700006X"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967590"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00963"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01072"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01161"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/3130800.3130883"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-008-0136-6"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00473"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6385773"},{"key":"ref67","article-title":"Kalib: Markerless hand-eye calibration with keypoint tracking","author":"Tang","year":"2024","journal-title":"CoRR, abs\/2408.10562"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_24"},{"key":"ref69","article-title":"Bundle adjustment-a mod-ern synthesis","volume-title":"Vision Algorithms: Theory and Practice: International Workshop on Vision Algorithms Corfu, Greece","author":"Triggs","year":"1999"},{"key":"ref70","article-title":"Marigold-dc: Zero-shot monocular depth completion with guided diffusion","author":"Viola","year":"2024","journal-title":"CoRR, abs\/2412.13389"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3572489"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00896"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02049"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00499"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01813"},{"key":"ref76","article-title":"Shape of motion: 4 d reconstruction from a single video","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00983"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00496"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01956"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341801"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-026-02810-6"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00084"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02112"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2018.xiv.019"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01650"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01929"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0688"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00389"},{"key":"ref90","author":"Zhang","year":"2025","journal-title":"Tapip3d: Tracking any point in persistent 3d geometry. arXiv preprint"},{"key":"ref91","article-title":"Monst3r: A simple approach for estimating geometry in the presence of motion","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19821-2_34"},{"key":"ref93","author":"Zhang","year":"2024","journal-title":"Cameras as rays: Pose estimation via ray diffusion. arXiv preprint"},{"key":"ref94","first-page":"20","article-title":"Freeman. Structure and motion from casual videos","author":"Zhang","year":"2022","journal-title":"ECCV"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19824-3_31"},{"key":"ref96","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\/11445086.pdf?arnumber=11445086","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:55:15Z","timestamp":1777611315000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445086\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":96,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00633","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}