{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:06:58Z","timestamp":1765339618268,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":49,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3754882","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T06:55:00Z","timestamp":1761375300000},"page":"7681-7690","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["SPHERE: Semantic-PHysical Engaged REpresentation for 3D Semantic Scene Completion"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0416-0576","authenticated-orcid":false,"given":"Zhiwen","family":"Yang","sequence":"first","affiliation":[{"name":"Wangxuan Institute of Computer Technology, Peking University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7658-3845","authenticated-orcid":false,"given":"Yuxin","family":"Peng","sequence":"additional","affiliation":[{"name":"Wangxuan Institute of Computer Technology, Peking University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00939"},{"key":"e_1_3_2_1_2_1","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition. 4413-4421","author":"Berman Maxim","year":"2018","unstructured":"Maxim Berman, Amal Rannen Triki, and Matthew B Blaschko. 2018. The lov\u00e1sz-softmax loss: A tractable surrogate for the optimization of the intersection-over-union measure in neural networks. In Proceedings of the IEEE conference on computer vision and pattern recognition. 4413-4421."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00396"},{"key":"e_1_3_2_1_4_1","volume-title":"Conference on Robot Learning. PMLR, 2148-2161","author":"Cheng Ran","year":"2021","unstructured":"Ran Cheng, Christopher Agia, Yuan Ren, Xinhai Li, and Liu Bingbing. 2021. S3cnet: A sparse semantic scene completion network for lidar point clouds. In Conference on Robot Learning. PMLR, 2148-2161."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01499"},{"key":"e_1_3_2_1_8_1","volume-title":"Bevdet: High-performance multi-camera 3d object detection in bird-eye-view. arXiv preprint arXiv:2112.11790","author":"Huang Junjie","year":"2021","unstructured":"Junjie Huang, Guan Huang, Zheng Zhu, Yun Ye, and Dalong Du. 2021. Bevdet: High-performance multi-camera 3d object detection in bird-eye-view. arXiv preprint arXiv:2112.11790 (2021)."},{"key":"e_1_3_2_1_9_1","volume-title":"Probabilistic Gaussian Superposition for Efficient 3D Occupancy Prediction. arXiv preprint arXiv:2412.04384","author":"Huang Yuanhui","year":"2024","unstructured":"Yuanhui Huang, Amonnut Thammatadatrakoon, Wenzhao Zheng, Yunpeng Zhang, Dalong Du, and Jiwen Lu. 2024a. Probabilistic Gaussian Superposition for Efficient 3D Occupancy Prediction. arXiv preprint arXiv:2412.04384 (2024)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00890"},{"key":"e_1_3_2_1_11_1","volume-title":"European Conference on Computer Vision. Springer, 376-393","author":"Huang Yuanhui","year":"2024","unstructured":"Yuanhui Huang, Wenzhao Zheng, Yunpeng Zhang, Jie Zhou, and Jiwen Lu. 2024b. Gaussianformer: Scene as gaussians for vision-based 3d semantic occupancy prediction. In European Conference on Computer Vision. Springer, 376-393."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01915"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02677"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160552"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25234"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25233"},{"key":"e_1_3_2_1_18_1","unstructured":"Yiming Li Sihang Li Xinhao Liu Moonjun Gong Kenan Li Nuo Chen Zijun Wang Zhiheng Li Tao Jiang Fisher Yu et al. 2023c. SSCBench: A Large-Scale 3D Semantic Scene Completion Benchmark for Autonomous Driving. arXiv preprint arXiv:2306.09001 (2023)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00877"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"e_1_3_2_1_22_1","volume-title":"Conference on Robot Learning. PMLR, 437-446","author":"Liu Zhi","year":"2023","unstructured":"Zhi Liu, Shaoyu Chen, Xiaojie Guo, Xinggang Wang, Tianheng Cheng, Hongmei Zhu, Qian Zhang, Wenyu Liu, and Yi Zhang. 2023. Vision-based uneven bev representation learning with polar rasterization and surface estimation. In Conference on Robot Learning. PMLR, 437-446."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_3_2_1_24_1","volume-title":"Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101","author":"Loshchilov Ilya","year":"2017","unstructured":"Ilya Loshchilov and Frank Hutter. 2017. Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01884"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3461989"},{"key":"e_1_3_2_1_27_1","volume-title":"Occdepth: A depth-aware method for 3d semantic scene completion. arXiv preprint arXiv:2302.13540","author":"Miao Ruihang","year":"2023","unstructured":"Ruihang Miao, Weizhou Liu, Mingrui Chen, Zheng Gong, Weixin Xu, Chen Hu, and Shuchang Zhou. 2023. Occdepth: A depth-aware method for 3d semantic scene completion. arXiv preprint arXiv:2302.13540 (2023)."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611537"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_12"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3095302"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/3DV50981.2020.00021"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01504-5"},{"key":"e_1_3_2_1_34_1","volume-title":"International conference on machine learning. PMLR, 6105-6114","author":"Tan Mingxing","year":"2019","unstructured":"Mingxing Tan and Quoc Le. 2019. Efficientnet: Rethinking model scaling for convolutional neural networks. In International conference on machine learning. PMLR, 6105-6114."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00772"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01401"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28384"},{"key":"e_1_3_2_1_38_1","volume-title":"Omni-Scene: Omni-Gaussian Representation for Ego-Centric Sparse-View Scene Reconstruction. arXiv preprint arXiv:2412.06273","author":"Wei Dongxu","year":"2024","unstructured":"Dongxu Wei, Zhiqi Li, and Peidong Liu. 2024. Omni-Scene: Omni-Gaussian Representation for Ego-Centric Sparse-View Scene Reconstruction. arXiv preprint arXiv:2412.06273 (2024)."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01920"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01692"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3344806"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16419"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00867"},{"key":"e_1_3_2_1_44_1","volume-title":"Depthssc: Depth-spatial alignment and dynamic voxel resolution for monocular 3d semantic scene completion. arXiv preprint arXiv:2311.17084","author":"Yao Jiawei","year":"2023","unstructured":"Jiawei Yao and Jusheng Zhang. 2023. Depthssc: Depth-spatial alignment and dynamic voxel resolution for monocular 3d semantic scene completion. arXiv preprint arXiv:2311.17084 (2023)."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1049\/cje.2021.00.455"},{"key":"e_1_3_2_1_46_1","volume-title":"Context and geometry aware voxel transformer for semantic scene completion. arXiv preprint arXiv:2405.13675","author":"Yu Zhu","year":"2024","unstructured":"Zhu Yu, Runmin Zhang, Jiacheng Ying, Junchen Yu, Xiaohai Hu, Lun Luo, Si-Yuan Cao, and Hui-Liang Shen. 2024. Context and geometry aware voxel transformer for semantic scene completion. arXiv preprint arXiv:2405.13675 (2024)."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00865"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.23919\/cje.2021.00.230"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.23919\/cje.2022.00.338"}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Dublin Ireland","acronym":"MM '25"},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3754882","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:03:12Z","timestamp":1765339392000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3754882"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":49,"alternative-id":["10.1145\/3746027.3754882","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3754882","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}