{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T13:03:16Z","timestamp":1784552596978,"version":"3.55.0"},"reference-count":78,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100010002","name":"Ministry of Education","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100010002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00640","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"6621-6632","source":"Crossref","is-referenced-by-count":1,"title":["OPFormer: Object Pose Estimation leveraging foundation model with geometric encoding"],"prefix":"10.1109","author":[{"given":"Artem","family":"Moroz","sequence":"first","affiliation":[{"name":"Czech Institute of Informatics, Robotics and Cybernetics, Czech Technical University in Prague"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"V\u00edt","family":"Zeman","sequence":"additional","affiliation":[{"name":"Czech Institute of Informatics, Robotics and Cybernetics, Czech Technical University in Prague"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Martin","family":"Mik\u0161\u00edk","sequence":"additional","affiliation":[{"name":"Czech Institute of Informatics, Robotics and Cybernetics, Czech Technical University in Prague"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Elizaveta","family":"Isianova","sequence":"additional","affiliation":[{"name":"Czech Institute of Informatics, Robotics and Cybernetics, Czech Technical University in Prague"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Miroslav","family":"David","sequence":"additional","affiliation":[{"name":"Czech Institute of Informatics, Robotics and Cybernetics, Czech Technical University in Prague"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pavel","family":"Burget","sequence":"additional","affiliation":[{"name":"Czech Institute of Informatics, Robotics and Cybernetics, Czech Technical University in Prague"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Varun","family":"Burde","sequence":"additional","affiliation":[{"name":"Czech Institute of Informatics, Robotics and Cybernetics, Czech Technical University in Prague"}],"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\/CVPR52734.2025.00662"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10605-2_35"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00745"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-91569-7_15"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73226-3_24"},{"key":"ref7","article-title":"Shapenet: An information-rich 3d model repository","author":"Chang","year":"2015"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00277"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00163"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00950"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00950"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01711"},{"key":"ref13","article-title":"Vision transformers need registers","volume-title":"International Conference on Learning Representations","author":"Darcet"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21105\/joss.04901"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00666"},{"key":"ref16","article-title":"Deep-6dpose: Recovering 6d object pose from a single rgb image","author":"Do","year":"2018"},{"key":"ref17","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"International Conference on Learning Representations","author":"Dosovitskiy"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.390"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811809"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.257"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i11.29096"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341672"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00663"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2544"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72684-2_17"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2017.103"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_2"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-66096-3_39"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00570"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00338"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.169"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_34"},{"key":"ref34","article-title":"Megapose: 6d pose estimation of novel objects via render & compare","volume-title":"Conference on Robot Learning","author":"Labb\u2019e"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01086"},{"key":"ref36","volume-title":"xformers: A modular and hackable transformer modelling library","author":"Lefaudeux","year":"2022"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/iccvw60793.2023.00226"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01250-9"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00777"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00354"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_2"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02636"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01287"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2858826"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01988"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19824-3_18"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19824-3_18"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/iros60139.2025.11245990"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00957"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01085"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530127"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759598"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00227"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00945"},{"key":"ref56","author":"Oquab","year":"2023","journal-title":"Dinov2: Learning robust visual features without supervision"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73347-5_10"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00776"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126342"},{"key":"ref60","article-title":"Pointnet++: Deep hierarchical feature learning on point sets in a metric space","author":"Qi","year":"2017"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.413"},{"key":"ref62","article-title":"Glu variants improve transformer","author":"M. Shazeer","year":"2020"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00671"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00662"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00670"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2018.00038"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_28"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981838"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.266"},{"key":"ref71","article-title":"Epnp: An accurate o(n) solution to the pnp problem","author":"Vincent","year":"2009","journal-title":"2009 International Journal of Computer Vision"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01634"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00275"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00275"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01692"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2018.xiv.019"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00669"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00203"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11492680.pdf?arnumber=11492680","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:16:14Z","timestamp":1778048174000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492680\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":78,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00640","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}