{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T09:33:16Z","timestamp":1763458396745,"version":"3.37.3"},"reference-count":41,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"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":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1109\/lra.2024.3501677","type":"journal-article","created":{"date-parts":[[2024,11,18]],"date-time":"2024-11-18T19:00:40Z","timestamp":1731956440000},"page":"11818-11825","source":"Crossref","is-referenced-by-count":2,"title":["Simultaneous Geometry and Pose Estimation of Held Objects Via 3D Foundation Models"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0958-6656","authenticated-orcid":false,"given":"Weiming","family":"Zhi","sequence":"first","affiliation":[{"name":"Robotics Institute, Carnegie Mellon University, Pittsburgh, PA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6719-846X","authenticated-orcid":false,"given":"Haozhan","family":"Tang","sequence":"additional","affiliation":[{"name":"Robotics Institute, Carnegie Mellon University, Pittsburgh, PA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6758-7203","authenticated-orcid":false,"given":"Tianyi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Robotics Institute, Carnegie Mellon University, Pittsburgh, PA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0506-907X","authenticated-orcid":false,"given":"Matthew","family":"Johnson-Roberson","sequence":"additional","affiliation":[{"name":"Robotics Institute, Carnegie Mellon University, Pittsburgh, PA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"article-title":"On the opportunities and risks of foundation models","year":"2021","author":"Bommasani","key":"ref1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1177\/02783649241281508"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01956"},{"article-title":"Machine perception of three-dimensional solids","year":"1963","author":"Roberts","key":"ref4"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01165"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_34"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00275"},{"key":"ref8","first-page":"715","article-title":"MegaPose: 6D pose estimation of novel objects via render & compare","volume-title":"Proc. 6th Conf. Robot Learn.","author":"Labb","year":"2022"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73347-5_10"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/iccvw60793.2023.00226"},{"key":"ref12","first-page":"1323","article-title":"iNeRF: Inverting neural radiance fields for pose estimation","volume-title":"Proc. 2021 IEEE\/RSJ Int. Conf. Intell. Robots Syst.","author":"Lin","year":"2021"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00066"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9635884"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01638"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793508"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/JRA.1987.1087096"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2931262"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/3877.003.0009"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.445"},{"issue":"4","key":"ref21","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3592433","article-title":"3D Gaussian splatting for real-time radiance field rendering","volume":"42","author":"Kerbl","year":"2023","journal-title":"ACM Trans. Graph."},{"article-title":"DarkGS: Learning neural illumination and 3D Gaussians relighting for robotic exploration in the dark","year":"2024","author":"Zhang","key":"ref22"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1561\/0600000052"},{"article-title":"OpenMVS: Multi-view stereo reconstruction library","year":"2020","author":"Cernea","key":"ref24"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_47"},{"article-title":"Llama: Open and efficient foundation language models","year":"2023","author":"Touvron","key":"ref26"},{"key":"ref27","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01692"},{"key":"ref30","article-title":"Cameras as rays: Pose estimation via ray diffusion","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang","year":"2024"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3451396"},{"key":"ref32","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1177\/027836499501400301"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/3DV53792.2021.00027"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref36","first-page":"1336","article-title":"Learning eye-in-hand camera calibration from a single image","volume-title":"Proc. Conf. Robot Learn.","author":"Valassakis","year":"2021"},{"article-title":"Grounded sam: Assembling open-world models for diverse visual tasks","year":"2024","author":"Ren","key":"ref37"},{"key":"ref38","first-page":"81","article-title":"Parallelised diffeomorphic sampling-based motion planning","volume-title":"Proc. Conf. Robot Learn.","author":"Lai","year":"2021"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1177\/02783640122067453"},{"key":"ref40","first-page":"508","article-title":"Diffeomorphic transforms for generalised imitation learning","volume-title":"Proc. Learn. Dyn. Control Conf.","author":"Zhi","year":"2022"},{"article-title":"Riemannian motion policies","year":"2018","author":"Ratliff","key":"ref41"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/10726578\/10756717.pdf?arnumber=10756717","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,23]],"date-time":"2024-12-23T19:38:33Z","timestamp":1734982713000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10756717\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":41,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/lra.2024.3501677","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"type":"electronic","value":"2377-3766"},{"type":"electronic","value":"2377-3774"}],"subject":[],"published":{"date-parts":[[2024,12]]}}}