{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T17:01:43Z","timestamp":1771952503473,"version":"3.50.1"},"reference-count":54,"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\/icra55743.2025.11128589","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"16020-16027","source":"Crossref","is-referenced-by-count":1,"title":["OmniShape: Zero-Shot Multi-Hypothesis Shape and Pose Estimation in the Real World"],"prefix":"10.1109","author":[{"given":"Katherine","family":"Liu","sequence":"first","affiliation":[{"name":"Toyota Research Institute,Los Altos,CA,USA,94022"}]},{"given":"Sergey","family":"Zakharov","sequence":"additional","affiliation":[{"name":"Toyota Research Institute,Los Altos,CA,USA,94022"}]},{"given":"Dian","family":"Chen","sequence":"additional","affiliation":[{"name":"Toyota Research Institute,Los Altos,CA,USA,94022"}]},{"given":"Takuya","family":"Ikeda","sequence":"additional","affiliation":[{"name":"Woven by Toyota,Chuo City,Tokyo,Japan,103_0022"}]},{"given":"Greg","family":"Shakhnarovich","sequence":"additional","affiliation":[{"name":"Toyota Research Institute,Los Altos,CA,USA,94022"}]},{"given":"Adrien","family":"Gaidon","sequence":"additional","affiliation":[{"name":"Toyota Research Institute,Los Altos,CA,USA,94022"}]},{"given":"Rares","family":"Ambrus","sequence":"additional","affiliation":[{"name":"Toyota Research Institute,Los Altos,CA,USA,94022"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Open-vocabulary object detection via vision and language knowledge distillation","author":"Gu","year":"2021","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/34.88573"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2003.1217599"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00945"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636708"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00203"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802487"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2021.3056043"},{"key":"ref10","article-title":"Generative category-level object pose estimation via diffusion models","volume":"36","author":"Zhang","year":"2024","journal-title":"Advances in Neural Information Processing Systems (NeuRIPS)"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01072"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00066"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_2"},{"key":"ref14","volume-title":"ShapeNet: An Information-Rich 3D Model Repository","author":"Chang","year":"2015"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00025"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00433"},{"key":"ref17","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. International Conference on Machine Learning (ICML)","author":"Radford"},{"key":"ref18","article-title":"Point-E: A system for generating 3D point clouds from complex prompts","author":"Nichol","year":"2022","journal-title":"arXiv preprint"},{"key":"ref19","first-page":"11 061","author":"Huang","year":"2023","journal-title":"Ze-roShape: Regression-based zero-shot shape reconstruction"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00875"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00960"},{"key":"ref22","article-title":"DreamGaussian: Generative gaussian splatting for efficient 3D content creation","author":"Tang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00275"},{"key":"ref24","first-page":"6840","article-title":"Denoising diffusion probabilistic mod-els","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref25","first-page":"8780","article-title":"Diffusion models beat GANS on image synthesis","volume":"34","author":"Dhariwal","year":"2021","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref26","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022","journal-title":"arXiv preprint"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73039-9_9"},{"key":"ref29","article-title":"SweetDreamer: Aligning geometric priors in 2D diffusion for consistent text-to-3D","author":"Li","year":"2023","journal-title":"arXiv preprint"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01565"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02000"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.207"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20086-1_16"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.00375"},{"key":"ref35","article-title":"One-2\u20133-45: Any single image to 3D mesh in 45 seconds without per-shape optimization","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref36","volume-title":"OpenLRM: Open-source large reconstruction models","author":"He","year":"2023"},{"key":"ref37","article-title":"Shap-E: Generating conditional 3D implicit functions","author":"Jun","year":"2023","journal-title":"arXiv preprint"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref39","volume-title":"Diffusers: State-of-the-art diffusion models","author":"von Platen","year":"2022"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-025-1562-4"},{"key":"ref41","article-title":"LRM: Large reconstruction model for single image to 3D","author":"Hong","year":"2023","journal-title":"arXiv preprint"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00853"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01072"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6385773"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref47","article-title":"SAM 2: Segment anything in images and videos","author":"Ravi","year":"2024","journal-title":"arXiv preprint"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/wacv61041.2025.00081"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20074-8_4"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00314"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981838"},{"key":"ref52","author":"Oquab","year":"2023","journal-title":"DINOv2: Learning robust visual features without supervision"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00911"},{"key":"ref54","volume-title":"ChatGPT: AI Language Model"}],"event":{"name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","location":"Atlanta, GA, USA","start":{"date-parts":[[2025,5,19]]},"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\/11128589.pdf?arnumber=11128589","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:08:08Z","timestamp":1756879688000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11128589\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11128589","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}