{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T09:27:46Z","timestamp":1780392466065,"version":"3.54.1"},"reference-count":94,"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\/iccv51701.2025.00563","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"5957-5968","source":"Crossref","is-referenced-by-count":1,"title":["MagicHOI: Leveraging 3D Priors for Accurate Hand-Object Reconstruction from Short Monocular Video Clips"],"prefix":"10.1109","author":[{"given":"Shibo","family":"Wang","sequence":"first","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou)"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haonan","family":"He","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou)"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maria","family":"Parelli","sequence":"additional","affiliation":[{"name":"ETH Zürich,Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christoph","family":"Gebhardt","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou)"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zicong","family":"Fan","sequence":"additional","affiliation":[{"name":"ETH Zürich,Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Song","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou)"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01110"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICAR.2015.7251504"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01219"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19824-3_20"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00839"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01239"},{"key":"ref7","article-title":"Putting the object back into video object segmentation","author":"Cheng","year":"2023","journal-title":"arXiv"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01992"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00508"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1554"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00623"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/3DV53792.2021.00011"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01244"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72698-9_25"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00054"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02157"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00152"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02019"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00326"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01638"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1017\/cbo9780511811685"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01208"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00065"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/3DV53792.2021.00075"},{"key":"ref26","article-title":"Detector-free structure from motion","author":"He","year":"2023","journal-title":"arxiv"},{"key":"ref27","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref28","article-title":"LRM: Large reconstruction model for single image to 3d","author":"Hong","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3550469.3555401"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_8"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/3DV50981.2020.00043"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02028"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73220-1_5"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01865"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00278"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_40"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00623"},{"key":"ref38","article-title":"Egohdm: An online egocentric-inertial human motion capture, localization, and dense mapping system","author":"Liu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00853"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01445"},{"key":"ref41","article-title":"SyncDreamer: Generating multiview-consistent images from a single-view image","author":"Liu","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00660"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00951"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20068-7_22"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01633"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_33"},{"key":"ref47","article-title":"A dataset of relighted 3d interacting hands","author":"Moon","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00013"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530127"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01249"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00938"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00938"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2209.14988"},{"key":"ref54","article-title":"Learning hand-held object reconstruction from in-the-wild videos","author":"Prakash","year":"2023","journal-title":"arXiv"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.01386"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3130800.3130883"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01300"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00499"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1023\/A:1014573219977"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_31"},{"key":"ref61","article-title":"Mvdream: Multi-view diffusion for 3d generation","author":"Shi","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.494"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00017"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_13"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01104"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00208"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-31439-6_100073"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73235-5_1"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00352"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00352"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00464"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/BF00129684"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00171"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01348"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-40602-7_14"},{"key":"ref76","article-title":"Pf-lrm: Pose-free large reconstruction model for joint pose and shape prediction","author":"Wang","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72751-1_4"},{"key":"ref78","article-title":"Reconstructing hand-held objects in 3d from images and videos","author":"Wu","year":"2024","journal-title":"Reconstructing hand-held objects in 3d from images and videos"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01091"},{"key":"ref80","article-title":"Volume rendering of neural implicit surfaces","volume-title":"NeurIPS","author":"Yariv","year":"2021"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00387"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00387"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01806"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00187"},{"key":"ref85","article-title":"Inpaint anything: Segment anything meets image inpainting","author":"Yu","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02581"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01116"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73347-5_22"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/3DV62453.2024.00016"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00244"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20062-5_1"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00539"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/3DV57658.2022.00073"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.525"}],"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\/11449027.pdf?arnumber=11449027","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:25:11Z","timestamp":1777530311000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11449027\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":94,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00563","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}