{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T15:54:53Z","timestamp":1778860493359,"version":"3.51.4"},"reference-count":67,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"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":[[2022,5,23]]},"DOI":"10.1109\/icra46639.2022.9811799","type":"proceedings-article","created":{"date-parts":[[2022,7,12]],"date-time":"2022-07-12T19:36:40Z","timestamp":1657654600000},"page":"10632-10640","source":"Crossref","is-referenced-by-count":74,"title":["CenterSnap: Single-Shot Multi-Object 3D Shape Reconstruction and Categorical 6D Pose and Size Estimation"],"prefix":"10.1109","author":[{"given":"Muhammad Zubair","family":"Irshad","sequence":"first","affiliation":[{"name":"Toyota Research Institute"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thomas","family":"Kollar","sequence":"additional","affiliation":[{"name":"Toyota Research Institute"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael","family":"Laskey","sequence":"additional","affiliation":[{"name":"Toyota Research Institute"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kevin","family":"Stone","sequence":"additional","affiliation":[{"name":"Toyota Research Institute"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zsolt","family":"Kira","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00456"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2018.00088"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_38"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00025"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.264"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00667"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206060"},{"key":"ref36","article-title":"Dense 3d object reconstruction from a single depth view","author":"yang","year":"2018","journal-title":"TPAMI"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00609"},{"key":"ref34","article-title":"AtlasNet: A Papier-Mache Approach to Learning 3D Surface Generation","author":"groueix","year":"0","journal-title":"Proceedings IEEE Conf on Computer Vision and Pattern Recognition (CVPR)"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3110538"},{"key":"ref62","first-page":"8024","article-title":"Pytorch: An imper-ative style, high-performance deep learning library","author":"paszke","year":"2019","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref61","author":"matl","year":"2019","journal-title":"Pyrender"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2009.V.021"},{"key":"ref28","article-title":"Objects as points","author":"zhou","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref64","article-title":"Open3D: A mod-ern library for 3D data processing","author":"zhou","year":"2018","journal-title":"ArXiv"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00705"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196679"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9635991"},{"key":"ref29","first-page":"474","article-title":"Tracking ob-jects as points","author":"zhou","year":"0","journal-title":"European Conference on Computer Vision"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00029"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2021.XVII.024"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2016.2645124"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00411"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00275"},{"key":"ref21","first-page":"530","article-title":"Shape prior deformation for categorical 6d object pose and size esti-mation","author":"tian","year":"0","journal-title":"European Conference on Computer Vision"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01243-8"},{"key":"ref26","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume":"28","author":"ren","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref59","first-page":"139","article-title":"Category level object pose estimation via neural analysis-by-synthesis","author":"chen","year":"0","journal-title":"European Conference on Computer Vision"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2019.00073"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00589"},{"key":"ref56","article-title":"Visualizing data using t-SNE","volume":"9","author":"van der maaten","year":"2008","journal-title":"Journal of Machine Learning Research"},{"key":"ref55","article-title":"ShapeNet: An information-rich 3d model repository","author":"chang","year":"2015","journal-title":"ArXiv Preprint"},{"key":"ref54","first-page":"652","article-title":"PointNet: Deep learning on point sets for 3d classification and segmentation","author":"qi","year":"0","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref53","first-page":"734","article-title":"CornerNet: Detecting objects as paired keypoints","author":"law","year":"0","journal-title":"Proceedings of the European Conference on Computer Vision (ECCV)"},{"key":"ref52","first-page":"6399","article-title":"Panop-tic feature pyramid networks","author":"kirillov","year":"0","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00356"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00459"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01473"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.1992.219918"},{"key":"ref13","first-page":"1521","article-title":"SDD-6D: Making RGB-based 3D detection and 6d pose estimation great again","author":"kehl","year":"0","journal-title":"Proceedings of the IEEE International Conference on Computer Vision"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.413"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.019"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00038"},{"key":"ref17","first-page":"4561","article-title":"PVNet: Pixel-wise voting network for 6dof pose esti-mation","author":"peng","year":"0","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00346"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00988"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00102"},{"key":"ref3","article-title":"SimNet: Enabling robust unknown ob-ject manipulation from pure synthetic data via stereo","author":"laskey","year":"0","journal-title":"5th Annual Conference on Robot Learning"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00872"},{"key":"ref5","first-page":"424","article-title":"3D object proposals for accurate object class detection","author":"chen","year":"2015","journal-title":"Advances in Neural Information Processing Systems Citeseer"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2795645"},{"key":"ref7","article-title":"Tota13DUnderstanding: Joint layout, object pose and mesh reconstruction for indoor scenes from a single image","author":"nie","year":"0","journal-title":"IEEE Conf Computer Vision and Pattern Recognition (CVPR)"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01099"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_16"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_17"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00933"},{"key":"ref48","first-page":"arxiv-2008","article-title":"Centerhmr: a bottom-up single-shot method for multi-person 3d mesh recovery from a single image","author":"sun","year":"2020","journal-title":"ArXiv e-prints"},{"key":"ref47","first-page":"649","article-title":"Solo: Segmenting objects by locations","author":"wang","year":"0","journal-title":"European Conference on Computer Vision"},{"key":"ref42","first-page":"699","article-title":"Implicit 3d orientation learning for 6d object detection from rgb images","author":"sundermeyer","year":"0","journal-title":"Proceedings of the European Conference on Computer Vision (ECCV)"},{"key":"ref41","first-page":"205","article-title":"Deep learning of local rgb-d patches for 3d object detection and 6d pose estimation","author":"kehl","year":"0","journal-title":"European Confer ence on Computer Vision"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01199"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_30"}],"event":{"name":"2022 IEEE International Conference on Robotics and Automation (ICRA)","location":"Philadelphia, PA, USA","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["2022 International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9811522\/9811357\/09811799.pdf?arnumber=9811799","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T23:06:45Z","timestamp":1667516805000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9811799\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":67,"URL":"https:\/\/doi.org\/10.1109\/icra46639.2022.9811799","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}