{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T16:01:00Z","timestamp":1784131260490,"version":"3.55.0"},"reference-count":51,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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":[[2025,10,19]]},"DOI":"10.1109\/iros60139.2025.11247066","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"4036-4043","source":"Crossref","is-referenced-by-count":1,"title":["MinkOcc: Towards real-time label-efficient semantic occupancy prediction"],"prefix":"10.1109","author":[{"given":"Samuel","family":"Sze","sequence":"first","affiliation":[{"name":"University of Oxford,Oxford Robotics Institute,Department of Engineering Science"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniele De","family":"Martini","sequence":"additional","affiliation":[{"name":"University of Oxford,Oxford Robotics Institute,Department of Engineering Science"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lars","family":"Kunze","sequence":"additional","affiliation":[{"name":"University of Oxford,Oxford Robotics Institute,Department of Engineering Science"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102671"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00396"},{"key":"ref3","article-title":"SSCBench: Monocular 3d semantic scene completion benchmark in street views","author":"Li","year":"2024"},{"key":"ref4","article-title":"Occ3d: A large-scale 3d occupancy prediction benchmark for autonomous driving","author":"Tian","year":"2023"},{"key":"ref5","article-title":"Openscene: The largest up-to-date 3d occupancy prediction benchmark in autonomous driving","author":"Contributors","year":"2023"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00939"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01636"},{"key":"ref10","article-title":"Occnerf: Advancing 3d occupancy prediction in lidar-free environments","author":"Zhang","year":"2024"},{"key":"ref11","article-title":"Selfocc: Self-supervised vision-based 3d occupancy prediction","author":"Huang","year":"2023"},{"key":"ref12","doi-asserted-by":"crossref","DOI":"10.1109\/ICRA57147.2024.10611537","article-title":"Renderocc: Vision-centric 3d occupancy prediction with 2d rendering supervision","author":"Pan","year":"2024"},{"key":"ref13","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v39i6.32698","article-title":"Semi-supervised 3d semantic scene completion with 2d vision foundation model guidance","author":"Pham","year":"2025"},{"key":"ref14","doi-asserted-by":"crossref","DOI":"10.1109\/IV55156.2024.10588696","article-title":"Real-time 3d semantic occupancy prediction for autonomous vehicles using memory-efficient sparse convolution","author":"Sze","year":"2024"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00319"},{"key":"ref16","article-title":"Pulsar: Efficient sphere-based neural rendering","author":"Lassner","year":"2020"},{"key":"ref17","article-title":"Grounding dino: Marrying dino with grounded pre-training for open-set object detection","author":"Liu","year":"2024"},{"key":"ref18","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV51070.2023.00371","article-title":"Segment anything","author":"Kirillov","year":"2023"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_12"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160831"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160968"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00890"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00472"},{"key":"ref25","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2019.01298","article-title":"Pointpillars: Fast encoders for object detection from point clouds","author":"Lang","year":"2019"},{"key":"ref26","article-title":"Occfusion: Depth estimation free multi-sensor fusion for 3d occupancy prediction","author":"Zhang","year":"2024"},{"key":"ref27","article-title":"Occfusion: Multi-sensor fusion framework for 3d semantic occupancy prediction","author":"Ming","year":"2024"},{"key":"ref28","article-title":"Robust 3d semantic occupancy prediction with calibration-free spatial transformation","author":"Zhuang","year":"2024"},{"key":"ref29","article-title":"Daocc: 3d object detection assisted multi-sensor fusion for 3d occupancy prediction","author":"Yang","year":"2024"},{"key":"ref30","article-title":"Mrocc: Efficient camera-lidar 3d semantic occupancy prediction using hierarchical multi-resolution voxel representation","author":"Seong","year":"2024"},{"key":"ref31","article-title":"Occloff: Learning optimized feature fusion for 3d occupancy prediction","author":"Zhang","year":"2024"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_18"},{"key":"ref33","article-title":"Regulating intermediate 3d features for vision-centric autonomous driving","author":"Xu","year":"2023"},{"key":"ref34","article-title":"Gsrender: Deduplicated occupancy prediction via weakly supervised 3d gaussian splatting","author":"Sun","year":"2024"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.54364\/aaiml.2024.42126"},{"key":"ref36","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-58452-8_24","article-title":"Nerf: Representing scenes as neural radiance fields for view synthesis","author":"Mildenhall","year":"2020"},{"key":"ref37","doi-asserted-by":"crossref","DOI":"10.1145\/3592433","article-title":"3d gaussian splatting for real-time radiance field rendering","author":"Kerbl","year":"2023"},{"key":"ref38","article-title":"3d representation methods: A survey","author":"Wang","year":"2024"},{"key":"ref39","article-title":"Gausstr: Foundation model-aligned gaussian transformer for self-supervised 3d spatial understanding","author":"Jiang","year":"2024"},{"key":"ref40","article-title":"Gaussianformer: Scene as gaussians for vision-based 3d semantic occupancy prediction","author":"Huang","year":"2024"},{"key":"ref41","article-title":"Gaussianformer-2: Probabilistic gaussian superposition for efficient 3d occupancy prediction","author":"Huang","year":"2024"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref43","doi-asserted-by":"crossref","DOI":"10.1109\/ICRA.2019.8794195","article-title":"Mvx-net: Multimodal voxelnet for 3d object detection","author":"Sindagi","year":"2019"},{"key":"ref44","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2018.00033","article-title":"Pointfusion: Deep sensor fusion for 3d bounding box estimation","author":"Xu","year":"2018"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref46","article-title":"Squeeze-and-excitation networks","author":"Hu","year":"2019"},{"key":"ref47","article-title":"Milo: Multi-task learning with localization ambiguity suppression for occupancy prediction","author":"Vu","year":"2023"},{"key":"ref48","doi-asserted-by":"crossref","DOI":"10.1109\/ICRA57147.2024.10610625","article-title":"Fastocc: Accelerating 3d occupancy prediction by fusing the 2d bird\u2019s-eye view and perspective view","author":"Hou","year":"2024"},{"key":"ref49","article-title":"FB-OCC: 3D occupancy prediction based on forward-backward view transformation","author":"Li","year":"2023"},{"key":"ref50","article-title":"Fully sparse 3d occupancy prediction","author":"Liu","year":"2024"},{"key":"ref51","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR52734.2025.01509","article-title":"Sparse voxels rasterization: Real-time high-fidelity radiance field rendering","author":"Sun","year":"2025"}],"event":{"name":"2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Hangzhou, China","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11245651\/11245652\/11247066.pdf?arnumber=11247066","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T12:37:44Z","timestamp":1766061464000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11247066\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":51,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11247066","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}