{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,2]],"date-time":"2025-08-02T16:54:26Z","timestamp":1754153666160,"version":"3.41.2"},"publisher-location":"Singapore","reference-count":31,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819698653"},{"type":"electronic","value":"9789819698660"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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\/978-981-96-9866-0_27","type":"book-chapter","created":{"date-parts":[[2025,7,23]],"date-time":"2025-07-23T09:26:01Z","timestamp":1753262761000},"page":"310-321","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["SGLFT-Occ: 3D Occupancy Prediction with Self-supervised Global Local Flatten Transformer"],"prefix":"10.1007","author":[{"given":"Jianping","family":"Li","sequence":"first","affiliation":[]},{"given":"Xiang","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Yanli","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Guozhen","family":"Tan","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,7,24]]},"reference":[{"key":"27_CR1","doi-asserted-by":"crossref","unstructured":"Huang, Y., Zheng, W., Zhang, B., Zhou, J., Lu, J.: SelfOcc: self-supervised vision-based 3D occupancy prediction. arXiv preprint arXiv:2311.12754 (2023)","DOI":"10.1109\/CVPR52733.2024.01885"},{"key":"27_CR2","doi-asserted-by":"crossref","unstructured":"Gan, W., Mo, N., Xu, H., Yokoya, N.: A simple attempt for 3D occupancy estimation in autonomous driving. arXiv preprint arXiv:2303.10076 (2023)","DOI":"10.1109\/TIV.2024.3403134"},{"key":"27_CR3","doi-asserted-by":"crossref","unstructured":"Hou, J., et al.: FastOcc: accelerating 3D occupancy prediction by fusing the 2D bird\u2019s-eye view and perspective view. arXiv preprint arXiv:2403.02710 (2024)","DOI":"10.1109\/ICRA57147.2024.10610625"},{"key":"27_CR4","doi-asserted-by":"crossref","unstructured":"Kulh\u00e1nek, J., Derner, E., Sattler, T., Babu\u0161ka, R.: ViewFormer: NeRF-free neural rendering from few images using transformers. In: European Conference on Computer Vision (ECCV) (2022)","DOI":"10.1007\/978-3-031-19784-0_12"},{"key":"27_CR5","doi-asserted-by":"crossref","unstructured":"Wang, Y., Chen, Y., Liao, X., Fan, L., Zhang, Z.: PanoOcc: Unified Occupancy Representation for Camera-Based 3D Panoptic Segmentation. arXiv preprint arXiv:2306.10013 (2023)","DOI":"10.1109\/CVPR52733.2024.01624"},{"key":"27_CR6","doi-asserted-by":"crossref","unstructured":"Xu, J., et al.: Regulating intermediate 3D features for vision-centric autonomous driving. In: AAAI Conf. on Artificial Intelligence, vol. 38, no. 6, pp. 6306\u20136314 (2024)","DOI":"10.1609\/aaai.v38i6.28449"},{"key":"27_CR7","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":"27_CR8","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":"27_CR9","unstructured":"Li, Z., et al.: FB-OCC: 3D Occupancy Prediction Based on Forward-Backward View Transformation. arXiv preprint arXiv:2307.01492 (2023)"},{"key":"27_CR10","unstructured":"Oquab, M., et al.: DINOv2: Learning Robust Visual Features Without Supervision. arXiv preprint arXiv:2304.07193 (2023)"},{"key":"27_CR11","doi-asserted-by":"crossref","unstructured":"Park, D., Ambrus, R., Guizilini, V., Li, J., Gaidon, A.: Is Pseudo-LiDAR needed for monocular 3D object detection? In: Proc. IEEE\/CVF Int. Conf. on Computer Vision, pp. 3142\u20133152 (2021)","DOI":"10.1109\/ICCV48922.2021.00313"},{"key":"27_CR12","doi-asserted-by":"crossref","unstructured":"Wang, T., Zhu, X., Pang, J., Lin, D.: FCOS3D: fully convolutional one-stage monocular 3D object detection. In: Proc. IEEE\/CVF Int. Conf. on Computer Vision, pp. 913\u2013922 (2021)","DOI":"10.1109\/ICCVW54120.2021.00107"},{"key":"27_CR13","unstructured":"Chen, Z., Li, Z., Zhang, S., Fang, L., Jiang, Q., Zhao, F.: BEVDistill: cross-modal BEV distillation for multi-view 3D object detection. arXiv preprint arXiv:2211.09386 (2022)"},{"key":"27_CR14","doi-asserted-by":"crossref","unstructured":"Min, C., Xiao, L., Zhao, D., Nie, Y., Dai, B.: UniScene: multi-camera unified pre-training via 3D scene reconstruction for autonomous driving. arXiv preprint arXiv:2305.18829 (2023)","DOI":"10.1109\/LRA.2024.3362635"},{"key":"27_CR15","doi-asserted-by":"crossref","unstructured":"Yang, Z., Chen, L., Sun, Y., Li, H.: Visual point cloud forecasting enables scalable autonomous driving. In: Proc. IEEE\/CVF Conf. on Computer Vision and Pattern Recognition, pp. 14673\u201314684 (2024)","DOI":"10.1109\/CVPR52733.2024.01390"},{"key":"27_CR16","doi-asserted-by":"crossref","unstructured":"Yang, H., et al.: UniPAD: a universal pre-training paradigm for autonomous driving. In: Proc. IEEE\/CVF Conf. on Computer Vision and Pattern Recognition, pp. 15238\u201315250 (2024)","DOI":"10.1109\/CVPR52733.2024.01443"},{"key":"27_CR17","doi-asserted-by":"crossref","unstructured":"Li, Z., Wang, W., Li, H., Xie, E., Sima, C., Lu, T., Qiao, Y., Dai, J.: 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":"27_CR18","unstructured":"Huang, J., Huang, G., Zhu, Z., Ye, Y., Du, D.: BEVDet: high-performance multi-camera 3D object detection in bird-eye-view. arXiv preprint arXiv:2112.11790 (2021)"},{"key":"27_CR19","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: BEVDepth: acquisition of reliable depth for multi-view 3D object detection. In: AAAI Conf. on Artificial Intelligence, vol. 37, no. 2, pp. 1477\u20131485 (2023)","DOI":"10.1609\/aaai.v37i2.25233"},{"key":"27_CR20","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proc. IEEE Conf. on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"27_CR21","doi-asserted-by":"crossref","unstructured":"Hu, A., et al.: FIERY: future instance prediction in bird\u2019s-eye view from surround monocular cameras. In: Proc. IEEE\/CVF Int. Conf. on Computer Vision, pp. 5273\u201315282 (2021)","DOI":"10.1109\/ICCV48922.2021.01499"},{"key":"27_CR22","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: VoxFormer: sparse voxel transformer for camera-based 3D semantic scene completion. In: Proc. IEEE\/CVF Conf. on Computer Vision and Pattern Recognition, pp. 9087\u20139098 (2023)","DOI":"10.1109\/CVPR52729.2023.00877"},{"key":"27_CR23","unstructured":"Tian, X., Jiang, T., Yun, L., Wang, Y., Zhao, H.: Occ3D: a large-scale 3D occupancy prediction benchmark for autonomous driving. arXiv preprint arXiv:2304.14365 (2023)"},{"key":"27_CR24","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. arXiv preprint arXiv:2302.07817 (2023)","DOI":"10.1109\/CVPR52729.2023.00890"},{"key":"27_CR25","unstructured":"Tian, X., Jiang, T., Yun, L., Wang, Y., Zhao, H.: Occ3D: a large-scale 3D occupancy prediction benchmark for autonomous driving. arXiv preprint arXiv:2304.14365 (2023)"},{"key":"27_CR26","doi-asserted-by":"crossref","unstructured":"Rold\u00e3o, L.: LMSCCNet: Lightweight Multiscale 3D Semantic Completion. In: Int. Conf. on 3D Vision (3DV) (2020)","DOI":"10.1109\/3DV50981.2020.00021"},{"key":"27_CR27","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: Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00425"},{"key":"27_CR28","doi-asserted-by":"crossref","unstructured":"Li, J., Han, K., Wang, P., Liu, Y., Yuan, X.: Anisotropic convolutional networks for 3D semantic scene completion. In: Proc. IEEE\/CVF Conf. on Computer Vision and Pattern Recognition, pp. 3351\u20133359 (2020)","DOI":"10.1109\/CVPR42600.2020.00341"},{"key":"27_CR29","doi-asserted-by":"crossref","unstructured":"Cao, A.-Q.: MonoScene: monocular 3D semantic scene completion. In: Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.00396"},{"key":"27_CR30","doi-asserted-by":"crossref","unstructured":"Yao, J., et al.: NDC-scene: boost monocular 3D semantic scene completion in normalized device coordinates space. In: Proc. IEEE\/CVF Int. Conf. on Computer Vision (ICCV), pp. 9455\u20139465 (2023)","DOI":"10.1109\/ICCV51070.2023.00867"},{"key":"27_CR31","doi-asserted-by":"crossref","unstructured":"Jiang, H., et al.: Symphonize 3D semantic scene completion with contextual instance queries. In: Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR) (2024)","DOI":"10.1109\/CVPR52733.2024.01915"}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-9866-0_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,23]],"date-time":"2025-07-23T09:26:33Z","timestamp":1753262793000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-9866-0_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819698653","9789819698660"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-9866-0_27","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"24 July 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Ningbo","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 July 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 July 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/icg\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}