{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T16:47:52Z","timestamp":1785775672231,"version":"3.56.0"},"reference-count":74,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00856","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"9158-9168","source":"Crossref","is-referenced-by-count":12,"title":["Easi3R: Estimating Disentangled Motion from DUSt3R Without Training"],"prefix":"10.1109","author":[{"given":"Xingyu","family":"Chen","sequence":"first","affiliation":[{"name":"Zhejiang University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yue","family":"Chen","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuliang","family":"Xiu","sequence":"additional","affiliation":[{"name":"Westlake University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andreas","family":"Geiger","sequence":"additional","affiliation":[{"name":"University of Tbingen, Tbingen AI Center"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anpei","family":"Chen","sequence":"additional","affiliation":[{"name":"Westlake University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0902-9"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/2001269.2001293"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15552-9_3"},{"key":"ref4","article-title":"Crossview completion models are zero-shot correspondence estimators","author":"An","year":"2024","journal-title":"arXiv"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2007.09.014"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72992-8_24"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15555-0_21"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00595"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.1049"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00060"},{"key":"ref11","article-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv preprint"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2658577"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10605-2_54"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2447"},{"key":"ref15","article-title":"Romo: Robust motion segmentation improves structure from motion","author":"Goli","year":"2024","journal-title":"arXiv preprint"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref17","article-title":"Prompt-to-prompt image editing with cross-attention control","volume-title":"International Conference on Learning Representations (ICLR)","author":"Hertz","year":"2023"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00193"},{"key":"ref19","article-title":"Stereo4d: Learning how things move in 3d from internet stereo videos","author":"Jin","year":"2024","journal-title":"arXiv"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01271"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3576"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00166"},{"key":"ref23","article-title":"Tapvid-3d: A benchmark for tracking any point in 3d","author":"Koppula","year":"2024","journal-title":"arXiv preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73220-1_5"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00981"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01401"},{"key":"ref27","article-title":"SLAM3R: real-time dense scene reconstruction from monocular RGB videos","author":"Liu","year":"2024","journal-title":"arXiv"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1023\/b:visi.0000029664.99615.94"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3386569.3392377"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/BF00127818"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3198480"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2015.2463671"},{"key":"ref33","article-title":"MASt3R-SLAM: real-time dense SLAM with 3d reconstruction priors","author":"Murai","year":"2024","journal-title":"arXiv"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126513"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.242"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73661-2_4"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01842"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.85"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00963"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1023\/A:1008109111715"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000025798.50602.3a"},{"key":"ref42","article-title":"The 2017 davis challenge on video object segmentation","author":"Pont-Tuset","year":"2017","journal-title":"arXiv preprint"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01196"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3019967"},{"key":"ref45","article-title":"Sam 2: Segment anything in images and videos","author":"Ravi","year":"2024","journal-title":"arXiv preprint"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00499"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.445"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02127"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459334"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/1141911.1141964"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-007-0107-3"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6385773"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"ref54","article-title":"Ba-net: Dense bundle adjustment network","author":"Tang","year":"2018","journal-title":"arXiv preprint"},{"key":"ref55","article-title":"MV-DU St3R+: single-stage scene reconstruction from sparse views in 2 seconds","author":"Tang","year":"2024","journal-title":"arXiv"},{"key":"ref56","article-title":"Droid-slam: Deep visual slam for monocular, stereo, and rgb-d cameras","author":"Teed","year":"2021","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1038\/382539a0"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-44480-7_21"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/34.88573"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/3dv66043.2025.00013"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02049"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00983"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01956"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341801"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72667-5_3"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2032"},{"key":"ref67","article-title":"DAS3R: dynamics-aware gaussian splatting for static scene reconstruction","author":"Xu","year":"2024","journal-title":"arXiv"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/11744085_8"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00709"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593691"},{"key":"ref72","author":"Zhang","year":"2025","journal-title":"MonST3R: a simple approach for estimating geometry in the presence of motion"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_2"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19824-3_31"}],"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\/11445612.pdf?arnumber=11445612","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:18:44Z","timestamp":1777529924000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445612\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":74,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00856","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}