{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T16:38:33Z","timestamp":1757608713424,"version":"3.44.0"},"reference-count":55,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"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":[[2025,5,19]]},"DOI":"10.1109\/icra55743.2025.11128515","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"1891-1898","source":"Crossref","is-referenced-by-count":0,"title":["CoL3D: Collaborative Learning of Single-view Depth and Camera Intrinsics for Metric 3D Shape Recovery"],"prefix":"10.1109","author":[{"given":"Chenghao","family":"Zhang","sequence":"first","affiliation":[{"name":"Alibaba Cloud Computing"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lubin","family":"Fan","sequence":"additional","affiliation":[{"name":"Alibaba Cloud Computing"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shen","family":"Cao","sequence":"additional","affiliation":[{"name":"Alibaba Cloud Computing"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bojian","family":"Wu","sequence":"additional","affiliation":[{"name":"Independent Researcher"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jieping","family":"Ye","sequence":"additional","affiliation":[{"name":"Alibaba Cloud Computing"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"9600","article-title":"3dp3: 3d scene perception via probabilistic programming","author":"Gothoskar","year":"2021","journal-title":"NeurIPS"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00119"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00400"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00389"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-023-1458-0"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02057"},{"key":"ref7","article-title":"Iebins: Iterative elastic bins for monocular depth estimation","author":"Shao","year":"2023","journal-title":"NeurIPS"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01660"},{"key":"ref9","article-title":"Tame a wild camera: In-the-wild monocular camera calibration","author":"Zhu","year":"2023","journal-title":"NeurIPS"},{"key":"ref10","first-page":"11826","article-title":"CAM-Convs: Camera-Aware Multi-Scale Convolutions for Single-View Depth","volume":"2019","author":"Facil","journal-title":"CVPR"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00830"},{"key":"ref12","first-page":"9233","article-title":"To-wards zero-shot scale-aware monocular depth estimation","author":"Guizilini","year":"2023","journal-title":"ICCV"},{"key":"ref13","first-page":"746","article-title":"Indoor segmen-tation and support inference from rgbd images","author":"Silberman","year":"2012","journal-title":"ECCV"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2010.170"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00391"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2377712"},{"key":"ref18","first-page":"52","article-title":"PixeI2mesh: Generating 3d mesh models from single rgb images","volume":"2018","author":"Wang","journal-title":"ECCV"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_40"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_22"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00239"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00016"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2008.132"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00027"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00175"},{"key":"ref26","article-title":"Depth map prediction from a single image using a multi-scale deep network","author":"Eigen","year":"2014","journal-title":"NeurIPS"},{"journal-title":"Va-depthnet: A variational approach to single image depth prediction","year":"2023","author":"Liu","key":"ref27"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2024.3416065"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19769-7_28"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01596"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01196"},{"journal-title":"Zoedepth: Zero-shot transfer by combining relative and metric depth","year":"2023","author":"Bhat","key":"ref32"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00847"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/34.888718"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2004.21"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2004.1315033"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.181"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248008"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-47979-1_12"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.1999.790349"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2008.300"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2011.06.001"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00250"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01592"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_32"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00963"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/34.9107"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298655"},{"journal-title":"From big to small: Multi-scale local planar guidance for monocular depth estimation","year":"2019","author":"Lee","key":"ref52"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00076"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.00166"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.166"}],"event":{"name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2025,5,19]]},"location":"Atlanta, GA, USA","end":{"date-parts":[[2025,5,23]]}},"container-title":["2025 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11127273\/11127223\/11128515.pdf?arnumber=11128515","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:12:25Z","timestamp":1756879945000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11128515\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11128515","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}