{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T01:03:05Z","timestamp":1784077385534,"version":"3.55.0"},"publisher-location":"Cham","reference-count":39,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031732416","type":"print"},{"value":"9783031732423","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T00:00:00Z","timestamp":1730160000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T00:00:00Z","timestamp":1730160000000},"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\/978-3-031-73242-3_7","type":"book-chapter","created":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T09:15:43Z","timestamp":1730106943000},"page":"110-126","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["FSD-BEV: Foreground Self-distillation for\u00a0Multi-view 3D Object Detection"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-9961-0951","authenticated-orcid":false,"given":"Zheng","family":"Jiang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7423-9266","authenticated-orcid":false,"given":"Jinqing","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1592-1067","authenticated-orcid":false,"given":"Yanan","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5181-6451","authenticated-orcid":false,"given":"Qingjie","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6106-0416","authenticated-orcid":false,"given":"Zhenghui","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Baohui","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8001-2703","authenticated-orcid":false,"given":"Yunhong","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,10,29]]},"reference":[{"key":"7_CR1","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":"7_CR2","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":"7_CR3","doi-asserted-by":"crossref","unstructured":"Dai, X., et al.: General instance distillation for object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7842\u20137851 (2021)","DOI":"10.1109\/CVPR46437.2021.00775"},{"key":"7_CR4","doi-asserted-by":"crossref","unstructured":"Guo, J., et al.: Distilling object detectors via decoupled features. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2154\u20132164 (2021)","DOI":"10.1109\/CVPR46437.2021.00219"},{"key":"7_CR5","doi-asserted-by":"crossref","unstructured":"Guo, X., Shi, S., Wang, X., Li, H.: LIGA-stereo: learning lidar geometry aware representations for stereo-based 3D detector. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3153\u20133163 (2021)","DOI":"10.1109\/ICCV48922.2021.00314"},{"key":"7_CR6","doi-asserted-by":"crossref","unstructured":"Hou, Y., Ma, Z., Liu, C., Hui, T.W., Loy, C.C.: Inter-region affinity distillation for road marking segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12486\u201312495 (2020)","DOI":"10.1109\/CVPR42600.2020.01250"},{"key":"7_CR7","unstructured":"Huang, J., Huang, G.: BEVDet4D: exploit temporal cues in multi-camera 3D object detection. arXiv preprint arXiv:2203.17054 (2022)"},{"key":"7_CR8","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":"7_CR9","unstructured":"Huang, P., et al.: TiG-BEV: multi-view BEV 3D object detection via target inner-geometry learning. arXiv preprint arXiv:2212.13979 (2022)"},{"key":"7_CR10","first-page":"18442","volume":"35","author":"Y Li","year":"2022","unstructured":"Li, Y., Chen, Y., Qi, X., Li, Z., Sun, J., Jia, J.: Unifying voxel-based representation with transformer for 3D object detection. Adv. Neural. Inf. Process. Syst. 35, 18442\u201318455 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"7_CR11","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: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a037, pp. 1486\u20131494 (2023)","DOI":"10.1609\/aaai.v37i2.25234"},{"key":"7_CR12","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: BEVDepth: acquisition of reliable depth for multi-view 3D object detection. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a037, pp. 1477\u20131485 (2023)","DOI":"10.1609\/aaai.v37i2.25233"},{"key":"7_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/978-3-031-20077-9_1","volume-title":"Computer Vision \u2013 ECCV 2022","author":"Z Li","year":"2022","unstructured":"Li, Z., et al.: BEVFormer: learning bird\u2019s-eye-view representation from multi-camera images via spatiotemporal transformers. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13669, pp. 1\u201318. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20077-9_1"},{"key":"7_CR14","doi-asserted-by":"crossref","unstructured":"Li, Z., Yu, Z., Wang, W., Anandkumar, A., Lu, T., Alvarez, J.M.: FB-BEV: BEV representation from forward-backward view transformations. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6919\u20136928 (2023)","DOI":"10.1109\/ICCV51070.2023.00637"},{"key":"7_CR15","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2117\u20132125 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"7_CR16","unstructured":"Lin, X., Lin, T., Pei, Z., Huang, L., Su, Z.: Sparse4D: multi-view 3D object detection with sparse spatial-temporal fusion. arXiv preprint arXiv:2211.10581 (2022)"},{"key":"7_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"531","DOI":"10.1007\/978-3-031-19812-0_31","volume-title":"Computer Vision \u2013 ECCV 2022","author":"Y Liu","year":"2022","unstructured":"Liu, Y., Wang, T., Zhang, X., Sun, J.: PETR: position embedding transformation for multi-view 3D object detection. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13687, pp. 531\u2013548. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19812-0_31"},{"key":"7_CR18","doi-asserted-by":"crossref","unstructured":"Liu, Y., Yan, J., Jia, F., Li, S., Gao, A., Wang, T., Zhang, X.: PETRv2: a unified framework for 3D perception from multi-camera images. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3262\u20133272 (2023)","DOI":"10.1109\/ICCV51070.2023.00302"},{"key":"7_CR19","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"7_CR20","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: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3142\u20133152 (2021)","DOI":"10.1109\/ICCV48922.2021.00313"},{"key":"7_CR21","unstructured":"Park, J., et al.: Time will tell: new outlooks and a baseline for temporal multi-view 3D object detection. arXiv preprint arXiv:2210.02443 (2022)"},{"key":"7_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"194","DOI":"10.1007\/978-3-030-58568-6_12","volume-title":"Computer Vision \u2013 ECCV 2020","author":"J Philion","year":"2020","unstructured":"Philion, J., Fidler, S.: Lift, splat, shoot: encoding images from arbitrary camera rigs by implicitly unprojecting to 3D. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020, Part XIV. LNCS, vol. 12359, pp. 194\u2013210. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58568-6_12"},{"key":"7_CR23","doi-asserted-by":"crossref","unstructured":"Wang, S., Liu, Y., Wang, T., Li, Y., Zhang, X.: Exploring object-centric temporal modeling for efficient multi-view 3D object detection. arXiv preprint arXiv:2303.11926 (2023)","DOI":"10.1109\/ICCV51070.2023.00335"},{"key":"7_CR24","unstructured":"Wang, T., Xinge, Z., Pang, J., Lin, D.: Probabilistic and geometric depth: detecting objects in perspective. In: Conference on Robot Learning, pp. 1475\u20131485. PMLR (2022)"},{"key":"7_CR25","doi-asserted-by":"crossref","unstructured":"Wang, T., Zhu, X., Pang, J., Lin, D.: FCOS3D: fully convolutional one-stage monocular 3D object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 913\u2013922 (2021)","DOI":"10.1109\/ICCVW54120.2021.00107"},{"key":"7_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":"7_CR27","unstructured":"Wang, Z., et al.: STS: surround-view temporal stereo for multi-view 3D detection. arXiv preprint arXiv:2208.10145 (2022)"},{"key":"7_CR28","doi-asserted-by":"crossref","unstructured":"Wang, Z., Li, D., Luo, C., Xie, C., Yang, X.: DistillBEV: boosting multi-camera 3D object detection with cross-modal knowledge distillation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8637\u20138646 (2023)","DOI":"10.1109\/ICCV51070.2023.00793"},{"key":"7_CR29","doi-asserted-by":"crossref","unstructured":"Yang, C., Xie, L., Su, C., Yuille, A.L.: Snapshot distillation: teacher-student optimization in one generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2859\u20132868 (2019)","DOI":"10.1109\/CVPR.2019.00297"},{"key":"7_CR30","doi-asserted-by":"crossref","unstructured":"Yang, C., et\u00a0al.: BEVFormer v2: adapting modern image backbones to bird\u2019s-eye-view recognition via perspective supervision. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17830\u201317839 (2023)","DOI":"10.1109\/CVPR52729.2023.01710"},{"key":"7_CR31","doi-asserted-by":"crossref","unstructured":"Yin, T., Zhou, X., Krahenbuhl, P.: Center-based 3D object detection and tracking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11784\u201311793 (2021)","DOI":"10.1109\/CVPR46437.2021.01161"},{"key":"7_CR32","doi-asserted-by":"crossref","unstructured":"Zhang, J., Zhang, Y., Liu, Q., Wang, Y.: SA-BEV: generating semantic-aware bird\u2019s-eye-view feature for multi-view 3D object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3348\u20133357 (2023)","DOI":"10.1109\/ICCV51070.2023.00310"},{"key":"7_CR33","doi-asserted-by":"crossref","unstructured":"Zhang, L., Song, J., Gao, A., Chen, J., Bao, C., Ma, K.: Be your own teacher: improve the performance of convolutional neural networks via self distillation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3713\u20133722 (2019)","DOI":"10.1109\/ICCV.2019.00381"},{"key":"7_CR34","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Huang, D., Wang, Y.: PC-RGNN: point cloud completion and graph neural network for 3D object detection. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a035, pp. 3430\u20133437 (2021)","DOI":"10.1609\/aaai.v35i4.16456"},{"key":"7_CR35","doi-asserted-by":"crossref","unstructured":"Zhou, C., Zhang, Y., Chen, J., Huang, D.: OCTR: octree-based transformer for 3D object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5166\u20135175 (2023)","DOI":"10.1109\/CVPR52729.2023.00500"},{"key":"7_CR36","doi-asserted-by":"crossref","unstructured":"Zhou, S., Liu, W., Hu, C., Zhou, S., Ma, C.: UniDistill: a universal cross-modality knowledge distillation framework for 3D object detection in bird\u2019s-eye view. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5116\u20135125 (2023)","DOI":"10.1109\/CVPR52729.2023.00495"},{"key":"7_CR37","unstructured":"Zhou, X., Wang, D., Kr\u00e4henb\u00fchl, P.: Objects as points. arXiv preprint arXiv:1904.07850 (2019)"},{"key":"7_CR38","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Tuzel, O.: VoxelNet: end-to-end learning for point cloud based 3D object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4490\u20134499 (2018)","DOI":"10.1109\/CVPR.2018.00472"},{"key":"7_CR39","unstructured":"Zhu, B., Jiang, Z., Zhou, X., Li, Z., Yu, G.: Class-balanced grouping and sampling for point cloud 3D object detection. arXiv preprint arXiv:1908.09492 (2019)"}],"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\/978-3-031-73242-3_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T09:27:49Z","timestamp":1730107669000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73242-3_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,29]]},"ISBN":["9783031732416","9783031732423"],"references-count":39,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73242-3_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,29]]},"assertion":[{"value":"29 October 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"}}]}}