{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:47:04Z","timestamp":1777657624990,"version":"3.51.4"},"publisher-location":"Cham","reference-count":34,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031730290","type":"print"},{"value":"9783031730306","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,24]],"date-time":"2024-11-24T00:00:00Z","timestamp":1732406400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,24]],"date-time":"2024-11-24T00:00:00Z","timestamp":1732406400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-73030-6_5","type":"book-chapter","created":{"date-parts":[[2024,11,25]],"date-time":"2024-11-25T16:56:40Z","timestamp":1732553800000},"page":"72-87","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":17,"title":["Occupancy as\u00a0Set of\u00a0Points"],"prefix":"10.1007","author":[{"given":"Yiang","family":"Shi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianheng","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qian","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenyu","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinggang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,24]]},"reference":[{"key":"5_CR1","doi-asserted-by":"crossref","unstructured":"Behley, J., et al.: Semantickitti: a dataset for semantic scene understanding of lidar sequences. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9297\u20139307 (2019)","DOI":"10.1109\/ICCV.2019.00939"},{"key":"5_CR2","doi-asserted-by":"crossref","unstructured":"Caesar, H., et al.: nuscenes: A multimodal dataset for autonomous driving. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11621\u201311631 (2020)","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"5_CR3","doi-asserted-by":"crossref","unstructured":"Cai, Y., Chen, X., Zhang, C., Lin, K.Y., Wang, X., Li, H.: Semantic scene completion via integrating instances and scene in-the-loop. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 324\u2013333 (2021)","DOI":"10.1109\/CVPR46437.2021.00039"},{"key":"5_CR4","doi-asserted-by":"crossref","unstructured":"Cao, A.Q., de\u00a0Charette, R.: Monoscene: monocular 3D semantic scene completion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3991\u20134001 (2022)","DOI":"10.1109\/CVPR52688.2022.00396"},{"key":"5_CR5","doi-asserted-by":"crossref","unstructured":"Chen, X., Lin, K.Y., Qian, C., Zeng, G., Li, H.: 3D sketch-aware semantic scene completion via semi-supervised structure prior. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4193\u20134202 (2020)","DOI":"10.1109\/CVPR42600.2020.00425"},{"key":"5_CR6","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"5_CR7","unstructured":"Huang, J., Huang, G., Zhu, Z., Du, D.: Bevdet: high-performance multi-camera 3D object detection in bird-eye-view. arXiv preprint arXiv:2112.11790 (2021)"},{"key":"5_CR8","unstructured":"Huang, J., Huang, G., Zhu, Z., Du, D.: Bevdet: high-performance multi-camera 3D object detection in bird-eye-view. CoRR (2021)"},{"key":"5_CR9","doi-asserted-by":"crossref","unstructured":"Huang, Y., Zheng, W., Zhang, Y., Zhou, J., Lu, J.: Tri-perspective view for vision-based 3D semantic occupancy prediction. In: CVPR, pp. 9223\u20139232 (2023)","DOI":"10.1109\/CVPR52729.2023.00890"},{"key":"5_CR10","doi-asserted-by":"crossref","unstructured":"Jiang, H., Cheng, T., Gao, N., Zhang, H., Liu, W., Wang, X.: Symphonize 3D semantic scene completion with contextual instance queries. CoRR (2023)","DOI":"10.1109\/CVPR52733.2024.01915"},{"key":"5_CR11","doi-asserted-by":"crossref","unstructured":"Li, J., Han, K., Wang, P., Liu, Y., Yuan, X.: Anisotropic convolutional networks for 3D semantic scene completion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3351\u20133359 (2020)","DOI":"10.1109\/CVPR42600.2020.00341"},{"key":"5_CR12","doi-asserted-by":"crossref","unstructured":"Li, J., et al.: RGBD based dimensional decomposition residual network for 3D semantic scene completion. In: CVPR, pp. 7693\u20137702 (2019)","DOI":"10.1109\/CVPR.2019.00788"},{"issue":"1","key":"5_CR13","doi-asserted-by":"publisher","first-page":"219","DOI":"10.1109\/LRA.2019.2953639","volume":"5","author":"J Li","year":"2019","unstructured":"Li, J., et al.: Depth based semantic scene completion with position importance aware loss. IEEE Robot. Autom. Lett. 5(1), 219\u2013226 (2019)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"5_CR14","doi-asserted-by":"crossref","unstructured":"Li, Y., Bao, H., Ge, Z., Yang, J., Sun, J., Li, Z.: Bevstereo: enhancing depth estimation in multi-view 3D object detection with temporal stereo. In: AAAI, pp. 1486\u20131494 (2023)","DOI":"10.1609\/aaai.v37i2.25234"},{"key":"5_CR15","doi-asserted-by":"crossref","unstructured":"Li, Z., et al.: Bevformer: learning bird\u2019s-eye-view representation from multi-camera images via spatiotemporal transformers. arXiv preprint arXiv:2203.17270 (2022)","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"5_CR16","unstructured":"Liu, S., et al.: See and think: disentangling semantic scene completion. In: Advances in Neural Information Processing Systems, vol.\u00a031 (2018)"},{"key":"5_CR17","doi-asserted-by":"crossref","unstructured":"Liu, Y., Wang, T., Zhang, X., Sun, J.: Petr: position embedding transformation for multi-view 3d object detection. arXiv preprint arXiv:2203.05625 (2022)","DOI":"10.1007\/978-3-031-19812-0_31"},{"key":"5_CR18","doi-asserted-by":"crossref","unstructured":"Liu, Y., et al.: Petrv2: a unified framework for 3D perception from multi-camera images. arXiv preprint arXiv:2206.01256 (2022)","DOI":"10.1109\/ICCV51070.2023.00302"},{"key":"5_CR19","unstructured":"Miao, R., et al.: Occdepth: a depth-aware method for 3D semantic scene completion (2023)"},{"key":"5_CR20","doi-asserted-by":"crossref","unstructured":"Moravec, H., Elfes, A.: High resolution maps from wide angle sonar. In: Proceedings. 1985 IEEE International Conference on Robotics and Automation, vol.\u00a02, pp. 116\u2013121. IEEE (1985)","DOI":"10.1109\/ROBOT.1985.1087316"},{"key":"5_CR21","doi-asserted-by":"crossref","unstructured":"Roldao, L., de\u00a0Charette, R., Verroust-Blondet, A.: LMSCnet: lightweight multiscale 3D semantic completion. In: 2020 International Conference on 3D Vision (3DV), pp. 111\u2013119. IEEE (2020)","DOI":"10.1109\/3DV50981.2020.00021"},{"key":"5_CR22","doi-asserted-by":"crossref","unstructured":"Song, S., Yu, F., Zeng, A., Chang, A.X., Savva, M., Funkhouser, T.: Semantic scene completion from a single depth image. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1746\u20131754 (2017)","DOI":"10.1109\/CVPR.2017.28"},{"key":"5_CR23","doi-asserted-by":"crossref","unstructured":"Sun, P., et\u00a0al.: Scalability in perception for autonomous driving: Waymo open dataset. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2446\u20132454 (2020)","DOI":"10.1109\/CVPR42600.2020.00252"},{"issue":"3","key":"5_CR24","doi-asserted-by":"publisher","first-page":"52","DOI":"10.1145\/504729.504754","volume":"45","author":"S Thrun","year":"2002","unstructured":"Thrun, S.: Probabilistic robotics. Commun. ACM 45(3), 52\u201357 (2002)","journal-title":"Commun. ACM"},{"key":"5_CR25","unstructured":"Tian, X., et al.: Occ3D: a large-scale 3D occupancy prediction benchmark for autonomous driving (2023)"},{"key":"5_CR26","doi-asserted-by":"crossref","unstructured":"Wang, T., Zhu, X., Pang, J., Lin, D.: Fcos3d: fully convolutional one-stage monocular 3D object detection. arXiv preprint arXiv:2104.10956 (2021)","DOI":"10.1109\/ICCVW54120.2021.00107"},{"key":"5_CR27","doi-asserted-by":"crossref","unstructured":"Wang, X., et al.: Openoccupancy: a large scale benchmark for surrounding semantic occupancy perception. arXiv preprint arXiv:2303.03991 (2023)","DOI":"10.1109\/ICCV51070.2023.01636"},{"key":"5_CR28","unstructured":"Wang, Y., Guizilini, V.C., Zhang, T., Wang, Y., Zhao, H., Solomon, J.: Detr3D: 3D object detection from multi-view images via 3D-to-2d queries. In: Conference on Robot Learning, pp. 180\u2013191. PMLR (2022)"},{"key":"5_CR29","doi-asserted-by":"crossref","unstructured":"Wei, Y., Zhao, L., Zheng, W., Zhu, Z., Zhou, J., Lu, J.: SurroundOCC: multi-camera 3D occupancy prediction for autonomous driving. arXiv preprint arXiv:2303.09551 (2023)","DOI":"10.1109\/ICCV51070.2023.01986"},{"key":"5_CR30","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"749","DOI":"10.1007\/978-3-030-01258-8_45","volume-title":"Computer Vision \u2013 ECCV 2018","author":"J Zhang","year":"2018","unstructured":"Zhang, J., Zhao, H., Yao, A., Chen, Y., Zhang, L., Liao, H.: Efficient semantic scene completion network with spatial group convolution. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11216, pp. 749\u2013765. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01258-8_45"},{"key":"5_CR31","doi-asserted-by":"crossref","unstructured":"Zhang, P., Liu, W., Lei, Y., Lu, H., Yang, X.: Cascaded context pyramid for full-resolution 3D semantic scene completion. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7801\u20137810 (2019)","DOI":"10.1109\/ICCV.2019.00789"},{"key":"5_CR32","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Zhu, Z., Du, D.: OCCformer: dual-path transformer for vision-based 3D semantic occupancy prediction. arXiv preprint arXiv:2304.05316 (2023)","DOI":"10.1109\/ICCV51070.2023.00865"},{"key":"5_CR33","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable DETR: deformable transformers for end-to-end object detection. In: International Conference on Learning Representations (2020)"},{"key":"5_CR34","unstructured":"Zuo, S., Zheng, W., Huang, Y., Zhou, J., Lu, J.: Pointocc: cylindrical tri-perspective view for point-based 3D semantic occupancy prediction (2023)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-73030-6_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,25]],"date-time":"2024-11-25T17:11:41Z","timestamp":1732554701000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73030-6_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,24]]},"ISBN":["9783031730290","9783031730306"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73030-6_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,24]]},"assertion":[{"value":"24 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}