{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T20:14:41Z","timestamp":1792786481803,"version":"4.5.0"},"reference-count":89,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/tdmrep.html"}],"funder":[{"name":"ONR","award":["N00014-23-1-2641"],"award-info":[{"award-number":["N00014-23-1-2641"]}]},{"name":"National Eye Institute","award":["R01EY037193"],"award-info":[{"award-number":["R01EY037193"]}],"id":[{"id":"https:\/\/ror.org\/03wkg3b53","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1109\/cvprf71909.2026.00131","type":"proceedings-article","created":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T19:23:58Z","timestamp":1791487438000},"page":"1314-1324","source":"Crossref","is-referenced-by-count":0,"title":["Fast Generative DeOcclusion for Vision and Robotics"],"prefix":"10.1109","author":[{"given":"Jieneng","family":"Chen","sequence":"first","affiliation":[{"name":"Johns Hopkins University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tiezheng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Johns Hopkins University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiwei","family":"Xuan","sequence":"additional","affiliation":[{"name":"Johns Hopkins University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ju","family":"He","sequence":"additional","affiliation":[{"name":"Johns Hopkins University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yifan","family":"Yin","sequence":"additional","affiliation":[{"name":"Johns Hopkins University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haojun","family":"Shi","sequence":"additional","affiliation":[{"name":"Johns Hopkins University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Suyu","family":"Ye","sequence":"additional","affiliation":[{"name":"Johns Hopkins University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinyi","family":"Li","sequence":"additional","affiliation":[{"name":"Johns Hopkins University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruisheng","family":"Yuan","sequence":"additional","affiliation":[{"name":"Johns Hopkins University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianmin","family":"Shu","sequence":"additional","affiliation":[{"name":"Johns Hopkins University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alan","family":"Yuille","sequence":"additional","affiliation":[{"name":"Johns Hopkins University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15552-9_3"},{"key":"ref2","article-title":"Do as i can, not as i say: Grounding language in robotic affordances","author":"Ahn","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/34.121791"},{"key":"ref4","article-title":"Receding horizon\u201d nextbest-view\u201d planner for 3d exploration","volume-title":"ICRA","author":"Bircher","year":"2016"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560956"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2016.2624754"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-32552-1_34"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/icra48891.2023.10161534"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00885"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00764"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794143"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.1049"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00643"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02492"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10605-2_54"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2023.3281153"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2403"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-091420-084139"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00548"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.18"},{"key":"ref22","article-title":"Compc: Completing a 3d point cloud with 2d diffusion priors","volume-title":"ICLR","author":"Huang","year":"2025"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02202"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.066"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11128540"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3436570"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72661-3_9"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913484072"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.23"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0534"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00401"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01807"},{"key":"ref33","article-title":"Openvla: An open-source vision-language-action model","author":"Kim","year":"2024","journal-title":"arXiv preprint arXiv"},{"issue":"1","key":"ref34","doi-asserted-by":"crossref","first-page":"XVIII","DOI":"10.1007\/BF00422382","article-title":"Gestalt psychology","volume":"31","author":"K\u00f6hler","year":"1967","journal-title":"Psychologische forschung"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_34"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02053"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73220-1_5"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00902"},{"key":"ref39","article-title":"Depth anything 3: Recovering the visual space from any views","volume-title":"ICLR","author":"Lin","year":"2026"},{"key":"ref40","article-title":"Ok-robot: What really matters in integrating open-knowledge models for robotics","author":"Liu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11127619"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657409"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2017.XIII.058"},{"key":"ref44","article-title":"Uniteam: Open vocabulary mobile manipulation challenge","author":"Melnik","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2024.3514143"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00299"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01556"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00377"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.02355"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00469"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00313"},{"key":"ref53","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford","year":"2021"},{"key":"ref54","article-title":"Grounded sam: Assembling open-world models for diverse visual tasks","author":"Ren","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00900"},{"key":"ref56","article-title":"Structurefrom-motion revisited","volume-title":"CVPR","author":"Schonberger","year":"2016"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-007-0107-3"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00128"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.695"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.090"},{"key":"ref61","article-title":"Droid-slam: Deep visual slam for monocular, stereo, and rgb-d cameras","volume-title":"NeurIPS","author":"Teed","year":"2021"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/34.88573"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793888"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00499"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00983"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00983"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01956"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01868"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2024.xx.077"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02036"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00858"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02000"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00545"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2018.xiv.019"},{"key":"ref75","article-title":"Sana: Efficient high-resolution image synthesis with linear diffusion transformers","volume-title":"ICLR","author":"Xie","year":"2025"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/lra.2025.3547643"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00029"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1145\/3730841"},{"key":"ref79","article-title":"Homerobot: Open-vocabulary mobile manipulation","author":"Yenamandra","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref80","article-title":"Inst-inpaint: Instructing to remove objects with diffusion models","author":"Burak Yildirim","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01227"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2018.00088"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00384"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28526"},{"key":"ref85","article-title":"Monst3r: A simple approach for estimating geometry in the presence of motion","volume-title":"ICLR","author":"Zhang","year":"2025"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00179"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/iros51168.2021.9636737"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.320"},{"key":"ref89","article-title":"Streaming 4d visual geometry transformer","author":"Zhuo","year":"2025","journal-title":"arXiv preprint arXiv"}],"event":{"name":"2026 IEEE\/CVF Conference on Computer Vision and Pattern Recognition- FINDINGS Track (CVPRF)","location":"Denver, CO, USA","start":{"date-parts":[[2026,6,3]]},"end":{"date-parts":[[2026,6,7]]}},"container-title":["2026 IEEE\/CVF Conference on Computer Vision and Pattern Recognition- FINDINGS Track (CVPRF)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11697600\/11697601\/11697701.pdf?arnumber=11697701","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,22]],"date-time":"2026-10-22T19:09:39Z","timestamp":1792696179000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11697701\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":89,"URL":"https:\/\/doi.org\/10.1109\/cvprf71909.2026.00131","relation":{},"subject":[],"published":{"date-parts":[[2026,6]]}}}