{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T16:38:22Z","timestamp":1757608702453,"version":"3.44.0"},"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\/icra55743.2025.11128732","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"4869-4876","source":"Crossref","is-referenced-by-count":0,"title":["H3O: Hyper-Efficient 3D Occupancy Prediction with Heterogeneous Supervision"],"prefix":"10.1109","author":[{"given":"Yunxiao","family":"Shi","sequence":"first","affiliation":[{"name":"Qualcomm Technologies, Inc.,Qualcomm AI Research"}]},{"given":"Hong","family":"Cai","sequence":"additional","affiliation":[{"name":"Qualcomm Technologies, Inc.,Qualcomm AI Research"}]},{"given":"Amin","family":"Ansari","sequence":"additional","affiliation":[{"name":"Qualcomm Technologies, Inc"}]},{"given":"Fatih","family":"Porikli","sequence":"additional","affiliation":[{"name":"Qualcomm Technologies, Inc.,Qualcomm AI Research"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01712"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01842"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00393"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.5244\/C.34.171"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00017"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01021"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00804"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72652-1_26"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00107"},{"key":"ref10","first-page":"180","article-title":"Detr3d: 3d object detection from multi-view images via 3d-to-2d queries","volume-title":"Conference on Robot Learning","author":"Wang","year":"2022"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.28033"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01710"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01636"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01986"},{"key":"ref16","article-title":"Occ3d: A large-scale 3d occupancy prediction benchmark for autonomous driving","volume":"36","author":"Tian","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01885"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2024.3403134"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00890"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3478513.3480496"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00865"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611537"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3444912"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00830"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00939"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00396"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00861"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00772"},{"volume-title":"Openscene: The largest up-to-date 3d occupancy prediction benchmark in autonomous driving","year":"2023","author":"Contributors","key":"ref30"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913491297"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14022"},{"journal-title":"Nerf++: Analyzing and improving neural radiance fields","year":"2020","author":"Zhang","key":"ref37"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01018"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00542"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00538"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530127"},{"journal-title":"Occnerf: Self-supervised multi-camera occupancy prediction with neural radiance fields","year":"2023","author":"Zhang","key":"ref42"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00580"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00541"},{"journal-title":"Neu-ral reflectance fields for appearance acquisition","year":"2020","author":"Bi","key":"ref45"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01245"},{"key":"ref47","first-page":"21 557","article-title":"Nerv: Neural representations for videos","volume":"34","author":"Chen","year":"2021","journal-title":"Advances in Neural Infor-mation Processing Systems"},{"key":"ref48","first-page":"25018","article-title":"Monosdf: Exploring monocular geometric cues for neural implicit surface reconstruction","volume":"35","author":"Yu","year":"2022","journal-title":"Advances in neural information processing systems"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00539"},{"key":"ref50","first-page":"1403","article-title":"Trans-formerfusion: Monocular rgb scene reconstruction using transformers","volume":"34","author":"Bozic","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58571-6_25"},{"journal-title":"Decoupled weight decay regularization","year":"2017","author":"Loshchilov","key":"ref52"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00341"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00877"}],"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\/11128732.pdf?arnumber=11128732","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:17:29Z","timestamp":1756880249000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11128732\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11128732","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}