{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,23]],"date-time":"2025-10-23T13:48:15Z","timestamp":1761227295502,"version":"build-2065373602"},"publisher-location":"Singapore","reference-count":30,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819521005","type":"print"},{"value":"9789819521012","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,10,24]],"date-time":"2025-10-24T00:00:00Z","timestamp":1761264000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,10,24]],"date-time":"2025-10-24T00:00:00Z","timestamp":1761264000000},"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":[[2026]]},"DOI":"10.1007\/978-981-95-2101-2_30","type":"book-chapter","created":{"date-parts":[[2025,10,23]],"date-time":"2025-10-23T13:26:59Z","timestamp":1761226019000},"page":"361-372","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["TGP: Two-Modal Occupancy Prediction with\u00a03D Gaussian and\u00a0Sparse Points for\u00a03D Environment Awareness"],"prefix":"10.1007","author":[{"given":"Mu","family":"Chen","sequence":"first","affiliation":[]},{"given":"Wenyu","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Mingchuan","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Yuan","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Tao","family":"Han","sequence":"additional","affiliation":[]},{"given":"Xinchi","family":"Li","sequence":"additional","affiliation":[]},{"given":"Guilong","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Huaici","family":"Zhao","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,10,24]]},"reference":[{"key":"30_CR1","doi-asserted-by":"crossref","unstructured":"Fan, H., Su, H., Guibas, L.: A point set generation network for 3D object reconstruction from a single image (2016). https:\/\/arxiv.org\/abs\/1612.00603","DOI":"10.1109\/CVPR.2017.264"},{"key":"30_CR2","doi-asserted-by":"crossref","unstructured":"Girish, S., Gupta, K., Shrivastava, A.: Eagles: efficient accelerated 3D gaussians with lightweight encodings. In: European Conference on Computer Vision, pp. 54\u201371. Springer (2024)","DOI":"10.1007\/978-3-031-73036-8_4"},{"key":"30_CR3","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":"30_CR4","unstructured":"Huang, J., Huang, G., Zhu, Z., Ye, Y., Du, D.: Bevdet: high-performance multi-camera 3D object detection in bird-eye-view (2022)"},{"key":"30_CR5","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 (2023). https:\/\/arxiv.org\/abs\/2302.07817","DOI":"10.1109\/CVPR52729.2023.00890"},{"key":"30_CR6","doi-asserted-by":"crossref","unstructured":"Huang, Y., Zheng, W., Zhang, Y., Zhou, J., Lu, J.: Gaussianformer: scene as gaussians for vision-based 3D semantic occupancy prediction (2024). https:\/\/arxiv.org\/abs\/2405.17429","DOI":"10.1007\/978-3-031-73383-3_22"},{"key":"30_CR7","doi-asserted-by":"crossref","unstructured":"Kerbl, B., Kopanas, G., Leimk\u00fchler, T., Drettakis, G.: 3D gaussian splatting for real-time radiance field rendering (2023). https:\/\/arxiv.org\/abs\/2308.04079","DOI":"10.1145\/3592433"},{"key":"30_CR8","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: Voxformer: sparse voxel transformer for camera-based 3d semantic scene completion (2023). https:\/\/arxiv.org\/abs\/2302.12251","DOI":"10.1109\/CVPR52729.2023.00877"},{"key":"30_CR9","doi-asserted-by":"crossref","unstructured":"Li, Z., et al.: Bevformer: learning bird\u2019s-eye-view representation from multi-camera images via spatiotemporal transformers (2022)","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"30_CR10","unstructured":"Li, Z., et al.: FB-OCC: 3D occupancy prediction based on forward-backward view transformation (2023). https:\/\/arxiv.org\/abs\/2307.01492"},{"key":"30_CR11","doi-asserted-by":"crossref","unstructured":"Liu, H., et al.: Fully sparse 3D occupancy prediction (2024). https:\/\/arxiv.org\/abs\/2312.17118","DOI":"10.1007\/978-3-031-72698-9_4"},{"key":"30_CR12","doi-asserted-by":"crossref","unstructured":"Liu, Y., Wang, T., Zhang, X., Sun, J.: Petr: position embedding transformation for multi-view 3D object detection. In: European Conference on Computer Vision, pp. 531\u2013548. Springer (2022)","DOI":"10.1007\/978-3-031-19812-0_31"},{"key":"30_CR13","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization (2019). https:\/\/arxiv.org\/abs\/1711.05101"},{"key":"30_CR14","doi-asserted-by":"crossref","unstructured":"Lu, T., et al.: Scaffold-GS: structured 3D gaussians for view-adaptive rendering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 20654\u201320664 (2024)","DOI":"10.1109\/CVPR52733.2024.01952"},{"key":"30_CR15","unstructured":"Mersch, B., Chen, X., Behley, J., Stachniss, C.: Self-supervised point cloud prediction using 3D spatio-temporal convolutional networks (2021). https:\/\/arxiv.org\/abs\/2110.04076"},{"key":"30_CR16","doi-asserted-by":"publisher","unstructured":"Mildenhall, B., Srinivasan, P.P., Tancik, M., Barron, J.T., Ramamoorthi, R., Ng, R.: Nerf: representing scenes as neural radiance fields for view synthesis. Commun. ACM 65(1), 99\u2013106 (2021). https:\/\/doi.org\/10.1145\/3503250","DOI":"10.1145\/3503250"},{"key":"30_CR17","doi-asserted-by":"crossref","unstructured":"Pan, M., et al.: Renderocc: vision-centric 3D occupancy prediction with 2D rendering supervision (2024). https:\/\/arxiv.org\/abs\/2309.09502","DOI":"10.1109\/ICRA57147.2024.10611537"},{"key":"30_CR18","unstructured":"Qi, Z., Ma, J., Xu, J., Zhou, Z., Cheng, L., Xiong, G.: GSPR: multimodal place recognition using 3D gaussian splatting for autonomous driving. arXiv preprint arXiv:2410.00299 (2024)"},{"issue":"9","key":"30_CR19","doi-asserted-by":"publisher","first-page":"6637","DOI":"10.1007\/s00521-021-06061-z","volume":"34","author":"P Qin","year":"2022","unstructured":"Qin, P., Zhang, C., Dang, M.: Gvnet: gaussian model with voxel-based 3D detection network for autonomous driving. Neural Comput. Appl. 34(9), 6637\u20136645 (2022)","journal-title":"Neural Comput. Appl."},{"issue":"4","key":"30_CR20","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3658187","volume":"43","author":"L Radl","year":"2024","unstructured":"Radl, L., Steiner, M., Parger, M., Weinrauch, A., Kerbl, B., Steinberger, M.: Stopthepop: sorted gaussian splatting for view-consistent real-time rendering. ACM Trans. Graph. (TOG) 43(4), 1\u201317 (2024)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"30_CR21","doi-asserted-by":"crossref","unstructured":"Shi, S., et al.: PV-RCNN: point-voxel feature set abstraction for 3D object detection (2021). https:\/\/arxiv.org\/abs\/1912.13192","DOI":"10.1109\/CVPR42600.2020.01054"},{"key":"30_CR22","unstructured":"Tian, X., et al.: OCC3D: a large-scale 3D occupancy prediction benchmark for autonomous driving (2023). https:\/\/arxiv.org\/abs\/2304.14365"},{"key":"30_CR23","unstructured":"Vaswani, A., et al.: Attention is all you need. arXiv (2017)"},{"key":"30_CR24","unstructured":"Wang, J., et al.: Opus: occupancy prediction using a sparse set (2024). https:\/\/arxiv.org\/abs\/2409.09350"},{"key":"30_CR25","doi-asserted-by":"crossref","unstructured":"Wang, X., et al.: Openoccupancy: a large scale benchmark for surrounding semantic occupancy perception (2023). https:\/\/arxiv.org\/abs\/2303.03991","DOI":"10.1109\/ICCV51070.2023.01636"},{"key":"30_CR26","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":"30_CR27","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 (2023). https:\/\/arxiv.org\/abs\/2303.09551","DOI":"10.1109\/ICCV51070.2023.01986"},{"key":"30_CR28","doi-asserted-by":"crossref","unstructured":"Yang, Z., Gao, X., Zhou, W., Jiao, S., Zhang, Y., Jin, X.: Deformable 3D gaussians for high-fidelity monocular dynamic scene reconstruction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 20331\u201320341 (2024)","DOI":"10.1109\/CVPR52733.2024.01922"},{"key":"30_CR29","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Zhu, Z., Du, D.: Occformer: dual-path transformer for vision-based 3D semantic occupancy prediction (2023). https:\/\/arxiv.org\/abs\/2304.05316","DOI":"10.1109\/ICCV51070.2023.00865"},{"key":"30_CR30","unstructured":"Zheng, W., et al.: Gaussianad: gaussian-centric end-to-end autonomous driving (2024). https:\/\/arxiv.org\/abs\/2412.10371"}],"container-title":["Lecture Notes in Computer Science","Intelligent Robotics and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-2101-2_30","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,23]],"date-time":"2025-10-23T13:27:10Z","timestamp":1761226030000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-2101-2_30"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,24]]},"ISBN":["9789819521005","9789819521012"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-2101-2_30","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,24]]},"assertion":[{"value":"24 October 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIRA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Robotics and Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Okayama","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","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":"6 August 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 August 2025","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":"icira2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.icira2025.com\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}