{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T06:04:34Z","timestamp":1784268274782,"version":"3.55.0"},"reference-count":83,"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\/iccv51701.2025.00773","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"8252-8263","source":"Crossref","is-referenced-by-count":2,"title":["MonoFusion: Sparse-View 4D Reconstruction via Monocular Fusion"],"prefix":"10.1109","author":[{"given":"Zihan","family":"Wang","sequence":"first","affiliation":[{"name":"Carnegie Mellon University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jeff","family":"Tan","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tarasha","family":"Khurana","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Neehar","family":"Peri","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Deva","family":"Ramanan","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Deep vit features as dense visual descriptors","author":"Amir","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/882262.882309"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1130"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3807511"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v40i4.37291"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72664-4_21"},{"key":"ref7","volume-title":"Vision transformers need registers","author":"Darcet","year":"2023"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/1360612.1360697"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01254"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/2897824.2925969"},{"key":"ref11","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":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01244"},{"key":"ref13","volume-title":"Instantsplat: Sparse-view gaussian splatting in seconds","author":"Fan","year":"2024"},{"key":"ref14","first-page":"21","volume":"17","author":"Forsyth","year":"2003","journal-title":"A modern approach. Computer vision: a modern approach"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00214"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72670-5_14"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00566"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00566"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2447"},{"key":"ref20","article-title":"Cat3d: Create anything in 3d with multi-view diffusion models","author":"Gao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01834"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3444912"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00583"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.59"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2782743"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00907"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02018"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.120"},{"key":"ref30","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv preprint arXiv"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.00998"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00578"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01879"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01963"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00643"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00643"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00416"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00981"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/wacv61041.2025.00262"},{"key":"ref40","article-title":"Towards understanding camera motions in any video","author":"Lin","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref41","article-title":"Drivingrecon: Large 4d gaussian reconstruction model for autonomous driving","author":"Lu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/3DV62453.2024.00044"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3322980"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298631"},{"key":"ref46","volume-title":"Dinov 2: Learning robust visual features without supervision","author":"Oquab","year":"2023"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.85"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00963"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3628473"},{"key":"ref50","first-page":"1227112292","article-title":"Livescene: Language embedding interactive radiance fields for physical scene control and rendering","volume-title":"Advances in Neural Information Processing Systems","author":"Qu","year":"2024"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01196"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3019967"},{"key":"ref53","article-title":"Sam 2: Segment anything in images and videos","author":"Ravi","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01042"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01620"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687681"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00972"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/3dv66043.2025.00028"},{"key":"ref59","article-title":"Ho-cap: A capture system and dataset for 3d reconstruction and pose tracking of handobject interaction","author":"Wang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref60","article-title":"Shape of motion: 4 d reconstruction from a single video","author":"Wang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00496"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01956"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801738"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00830"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01920"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02036"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1145\/3687759"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00288"},{"key":"ref69","article-title":"Storm: Spatio-temporal reconstruction model for large-scale outdoor scenes","author":"Yang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"ref71","article-title":"Depth anything v2","author":"Yang","year":"2024","journal-title":"arXiv"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01922"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/IROS60139.2025.11246221"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00455"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3613256"},{"key":"ref76","volume-title":"Pypose v0.6: The imperative programming interface for robotics","author":"Zhan","year":"2023"},{"key":"ref77","article-title":"Monst3r: A simple approach for estimating geometry in the presence of motion","author":"Zhang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00592"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/tmech.2025.3556283"},{"key":"ref81","volume-title":"Learning efficient robotic garment manipulation with standardization","author":"Zhou","year":"2025"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02048"},{"key":"ref83","article-title":"FSGS: real-time few-shot view synthesis using gaussian splatting","volume":"abs\/2312.00451","author":"Zhu","year":"2023","journal-title":"CoRR"}],"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\/11443384.pdf?arnumber=11443384","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:21:17Z","timestamp":1777530077000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443384\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":83,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00773","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}