{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T15:20:07Z","timestamp":1782314407521,"version":"3.54.5"},"reference-count":61,"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\/iccv51701.2025.00851","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"9700-9710","source":"Crossref","is-referenced-by-count":1,"title":["RayPose: Ray Bundling Diffusion for Template Views in Unseen 6D Object Pose Estimation"],"prefix":"10.1109","author":[{"given":"Junwen","family":"Huang","sequence":"first","affiliation":[{"name":"Technical University of Munich"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shishir Reddy","family":"Vutukur","sequence":"additional","affiliation":[{"name":"Technical University of Munich"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peter KT","family":"Yu","sequence":"additional","affiliation":[{"name":"XYZ Robotics"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nassir","family":"Navab","sequence":"additional","affiliation":[{"name":"Technical University of Munich"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Slobodan","family":"Ilic","sequence":"additional","affiliation":[{"name":"Technical University of Munich"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Benjamin","family":"Busam","sequence":"additional","affiliation":[{"name":"Technical University of Munich"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611464"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00753"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10605-2_35"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00668"},{"key":"ref5","article-title":"Shapenet: An information-rich 3d model repository","author":"Chang","year":"2015","journal-title":"arXiv preprint"},{"key":"ref6","author":"Chen","year":"2023","journal-title":"Zeropose: Cad-model-based zeroshot pose estimation"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00950"},{"key":"ref8","article-title":"Blenderproc","author":"Denninger","year":"2019","journal-title":"arXiv preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.390"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811809"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1017\/cbo9780511811685"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00663"},{"key":"ref14","article-title":"Onepose++: Keypoint-free one-shot object pose estimation without CAD models","author":"He","year":"2022","journal-title":"NeurIPS"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2017.103"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_2"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00041"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00962"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00962"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802487"},{"key":"ref21","article-title":"Perceiver io: A general architecture for structured inputs & outputs","author":"Jaegle","year":"2021","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref22","article-title":"Housecat6d-a large-scale multi-modal category level 6d object pose dataset with household objects in realistic scenarios","author":"Jung","year":"2022","journal-title":"arXiv preprint"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.169"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_34"},{"key":"ref26","article-title":"Megapose: 6d pose estimation of novel objects via render & compare","author":"Labb\u00e9","year":"2022","journal-title":"CoRL"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i4.28072"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02529"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2019.00777"},{"key":"ref30","article-title":"Hunyuan-dit: A powerful multi-resolution diffusion transformer with fine-grained chinese understanding","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/3DV62453.2024.00126"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02636"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3552132"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19824-3_18"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01051"},{"key":"ref36","article-title":"Zero-shot novel view and depth synthesis with multi-view geometric diffusion","volume-title":"arXiv preprint","author":"Luo","year":"2023"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00957"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00227"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00945"},{"key":"ref41","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"arXiv preprint"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73347-5_10"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref44","article-title":"Analytisch-geometrische Entwicklungen","author":"Pl\u00fccker","year":"1828","journal-title":"GD Baedeker"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.445"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00671"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00671"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00662"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00670"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00279"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2229"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72640-8_10"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01634"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00275"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00896"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01692"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2018.xiv.019"},{"key":"ref58","article-title":"Mvdream: Multi-view diffusion for 3d generation","author":"Zhang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref59","article-title":"Cameras as rays: Pose estimation via ray diffusion","volume-title":"International Conference on Learning Representations (ICLR)","author":"Y. Zhang"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01291"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00847"}],"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\/11445024.pdf?arnumber=11445024","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:31:13Z","timestamp":1777613473000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445024\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":61,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00851","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}