{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:28:35Z","timestamp":1777865315699,"version":"3.51.4"},"reference-count":91,"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":["62176135"],"award-info":[{"award-number":["62176135"]}],"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\/iccv51701.2025.00829","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"8863-8874","source":"Crossref","is-referenced-by-count":0,"title":["Self-Supervised Monocular 4D Scene Reconstruction for Egocentric Videos"],"prefix":"10.1109","author":[{"given":"Chengbo","family":"Yuan","sequence":"first","affiliation":[{"name":"Institute for Interdisciplinary Information Sciences, Tsinghua University"}]},{"given":"Geng","family":"Chen","sequence":"additional","affiliation":[{"name":"Shanghai Qi Zhi Institute"}]},{"given":"Li","family":"Yi","sequence":"additional","affiliation":[{"name":"Institute for Interdisciplinary Information Sciences, Tsinghua University"}]},{"given":"Yang","family":"Gao","sequence":"additional","affiliation":[{"name":"Institute for Interdisciplinary Information Sciences, Tsinghua University"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19769-7_40"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01324"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01260"},{"key":"ref4","article-title":"Zoedepth: Zero-shot transfer by combining relative and metric depth","author":"Farooq Bhat","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref5","article-title":"Unsupervised scale-consistent depth and ego-motion learning from monocular video","volume":"32","author":"Bian","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref6","article-title":"Midas v3. 1-a model zoo for robust monocular relative depth estimation","author":"Birkl","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2021.3075644"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01876"},{"key":"ref9","article-title":"Vision transformer adapter for dense predictions","author":"Chen","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00259"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3048"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46723-8_49"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.105"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01531-2"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/3dv66043.2025.00008"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01563"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01244"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00050"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01842"},{"key":"ref20","article-title":"Deep relu networks have surprisingly few activation patterns","volume":"32","author":"Hanin","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00193"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00982"},{"key":"ref23","article-title":"Co-tracker: It is better to track together","author":"Karaev","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3047"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"ref26","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv preprint arXiv"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00166"},{"key":"ref28","article-title":"Tapvid-3d: A benchmark for tracking any point in 3d","author":"Koppula","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00998"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00578"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02033"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00981"},{"key":"ref33","article-title":"Feed-forward bullet-time reconstruction of dynamic scenes from monocular videos","author":"Liang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref34","first-page":"1950","volume":"35","author":"Liu","year":"2022","journal-title":"Fewshot parameter-efficient fine-tuning is better and cheaper than in-context learning. Advances in Neural Information Processing Systems"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2023.12.020"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02034"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00010"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02125"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/3dv62453.2024.00044"},{"key":"ref40","article-title":"Embodiedgpt: Vision-language pre-training via embodied chain of thought","volume":"36","author":"Mu","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2015.2463671"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01556"},{"key":"ref43","article-title":"R3m: A universal visual representation for robot manipulation","author":"Nair","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref44","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref45","article-title":"From 2d to 3d: Re-thinking benchmarking of monocular depth prediction","author":"\u00d6rnek","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01842"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00938"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00963"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01143"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00487"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00754"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3196104"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3677327"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341922"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/1921264.1921293"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.445"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_31"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00989"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160657"},{"key":"ref60","article-title":"Flowcam: training generalizable 3d radiance fields without camera poses via pixel-aligned scene flow","author":"Smith","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/3dv66043.2025.00041"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01445"},{"key":"ref63","article-title":"Kick back & relax++: Scaling beyond groundtruth depth with slowtv & cribstv","author":"Spencer","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01954"},{"key":"ref65","article-title":"Dynamo-depth: fixing unsupervised depth estimation for dynamical scenes","volume":"36","author":"Sun","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref66","first-page":"16558","article-title":"Droid-slam: Deep visual slam for monocular, stereo, and rgb-d cameras","volume":"34","author":"Teed","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref67","author":"Vantage","journal-title":"Cutting edge, flagship camera with intelligent feedback and resolution"},{"key":"ref68","author":"Vaswani","year":"2017","journal-title":"Attention is all you need. Advances in Neural Information Processing Systems"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.1999.790293"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/3dv66043.2025.00013"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02049"},{"key":"ref72","article-title":"Shape of motion: 4 d reconstruction from a single video","author":"Wang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00983"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43996-4_42"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01956"},{"key":"ref76","first-page":"1761","article-title":"Tartanvo: A generalizable learning-based vo","volume-title":"Conference on Robot Learning","author":"Wang","year":"2021"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00868"},{"key":"ref78","article-title":"Egocentric video comprehension via large language model inner speech","volume-title":"3rd International Ego4D Workshop","author":"Wang","year":"2023"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2024.xx.092"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00795"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-11021-5_43"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00830"},{"key":"ref84","article-title":"General flow as foundation affordance for scalable robot learning","author":"Yuan","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.15062"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/3dv66043.2025.00105"},{"key":"ref87","article-title":"Monst3r: A simple approach for estimating geometry in the presence of motion","author":"Zhang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19818-2_8"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00345"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_2"},{"key":"ref91","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\/11445731.pdf?arnumber=11445731","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:15:39Z","timestamp":1777529739000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445731\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":91,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00829","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}