{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,2]],"date-time":"2026-08-02T18:37:08Z","timestamp":1785695828086,"version":"3.56.0"},"publisher-location":"Cham","reference-count":47,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031726262","type":"print"},{"value":"9783031726279","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,20]],"date-time":"2024-10-20T00:00:00Z","timestamp":1729382400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,20]],"date-time":"2024-10-20T00:00:00Z","timestamp":1729382400000},"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\/978-3-031-72627-9_1","type":"book-chapter","created":{"date-parts":[[2024,10,19]],"date-time":"2024-10-19T21:02:10Z","timestamp":1729371730000},"page":"1-17","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["SimPB: A Single Model for\u00a02D and\u00a03D Object Detection from\u00a0Multiple Cameras"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3000-9407","authenticated-orcid":false,"given":"Yingqi","family":"Tang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-3772-4258","authenticated-orcid":false,"given":"Zhaotie","family":"Meng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1687-6122","authenticated-orcid":false,"given":"Guoliang","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7941-6911","authenticated-orcid":false,"given":"Erkang","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,10,20]]},"reference":[{"key":"1_CR1","doi-asserted-by":"crossref","unstructured":"Brazil, G., Liu, X.: M3D-RPN: monocular 3D region proposal network for object detection. In: ICCV, pp. 9287\u20139296 (2019)","DOI":"10.1109\/ICCV.2019.00938"},{"key":"1_CR2","doi-asserted-by":"crossref","unstructured":"Caesar, H., et al.: nuScenes: a multimodal dataset for autonomous driving. In: CVPR, pp. 11618\u201311628 (2020)","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"1_CR3","doi-asserted-by":"crossref","unstructured":"Cai, Z., Vasconcelos, N.: Cascade R-CNN: delving into high quality object detection. In: CVPR, pp. 6154\u20136162 (2018)","DOI":"10.1109\/CVPR.2018.00644"},{"key":"1_CR4","doi-asserted-by":"crossref","unstructured":"Chen, X., Kundu, K., Zhang, Z., Ma, H., Fidler, S., Urtasun, R.: Monocular 3D object detection for autonomous driving. In: CVPR, pp. 2147\u20132156 (2016)","DOI":"10.1109\/CVPR.2016.236"},{"key":"1_CR5","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: CVPR, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"1_CR6","doi-asserted-by":"crossref","unstructured":"Duan, K., Bai, S., Xie, L., Qi, H., Huang, Q., Tian, Q.: CenterNet: keypoint triplets for object detection. In: ICCV, pp. 6569\u20136578 (2019)","DOI":"10.1109\/ICCV.2019.00667"},{"key":"1_CR7","doi-asserted-by":"crossref","unstructured":"Han, C., et al.: Exploring recurrent long-term temporal fusion for multi-view 3D perception. arXiv preprint arXiv:2303.05970 (2023)","DOI":"10.1109\/LRA.2024.3401172"},{"key":"1_CR8","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":"1_CR9","unstructured":"Huang, J., Huang, G.: BEVDet4D: exploit temporal cues in multi-camera 3D object detection. arXiv preprint arXiv:2203.17054 (2022)"},{"key":"1_CR10","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":"1_CR11","doi-asserted-by":"crossref","unstructured":"Jiang, X., et al.: Far3D: expanding the horizon for surround-view 3D object detection. In: AAAI (2023)","DOI":"10.1609\/aaai.v38i3.28033"},{"key":"1_CR12","doi-asserted-by":"crossref","unstructured":"Lee, Y., Hwang, J.W., Lee, S., Bae, Y., Park, J.: An energy and GPU-computation efficient backbone network for real-time object detection. In: CVPR (2019)","DOI":"10.1109\/CVPRW.2019.00103"},{"key":"1_CR13","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":"1_CR14","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: BEVDepth: acquisition of reliable depth for multi-view 3D object detection. In: AAAI, pp. 1477\u20131485 (2023)","DOI":"10.1609\/aaai.v37i2.25233"},{"key":"1_CR15","doi-asserted-by":"crossref","unstructured":"Li, Z., Lan, S., Alvarez, J.M., Wu, Z.: BEVNeXt: reviving dense BEV frameworks for 3D object detection. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.01901"},{"key":"1_CR16","doi-asserted-by":"crossref","unstructured":"Li, Z., et al.: BEVFormer: learning bird\u2019s-eye-view representation from multi-camera images via spatiotemporal transformers. In: ECCV, pp. 1\u201318 (2022)","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"1_CR17","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) Computer Vision \u2013 ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V, pp. 740\u2013755. Springer International Publishing, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"1_CR18","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":"1_CR19","unstructured":"Lin, X., Lin, T., Pei, Z., Huang, L., Su, Z.: Sparse4D v2: recurrent temporal fusion with sparse model. arXiv preprint arXiv:2305.14018 (2023)"},{"key":"1_CR20","unstructured":"Lin, X., Pei, Z., Lin, T., Huang, L., Su, Z.: Sparse4D v3: advancing end-to-end 3D detection and tracking. arXiv preprint arXiv:2311.11722 (2023)"},{"key":"1_CR21","doi-asserted-by":"crossref","unstructured":"Liu, H., Teng, Y., Lu, T., Wang, H., Wang, L.: SparseBEV: high-performance sparse 3D object detection from multi-camera videos. In: ICCV, pp. 18580\u201318590 (2023)","DOI":"10.1109\/ICCV51070.2023.01703"},{"key":"1_CR22","unstructured":"Liu, S., Li, F., Zhang, H., Yang, X., Qi, X., Su, H., Zhu, J., Zhang, L.: DAB-DETR: dynamic anchor boxes are better queries for DETR. In: ICLR (2022)"},{"key":"1_CR23","doi-asserted-by":"crossref","unstructured":"Liu, Y., Wang, T., Zhang, X., Sun, J.: Petr: Position embedding transformation for multi-view 3D object detection. In: ECCV, pp. 531\u2013548 (2022)","DOI":"10.1007\/978-3-031-19812-0_31"},{"key":"1_CR24","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":"1_CR25","unstructured":"Luo, Z., Zhou, C., Zhang, G., Lu, S.: DETR4d: direct multi-view 3D object detection with sparse attention. arXiv preprint arXiv:2212.07849 (2022)"},{"key":"1_CR26","doi-asserted-by":"crossref","unstructured":"Meng, D., et al.: Conditional DETR for fast training convergence. In: ICCV, pp. 3651\u20133660 (2021)","DOI":"10.1109\/ICCV48922.2021.00363"},{"key":"1_CR27","doi-asserted-by":"crossref","unstructured":"Mousavian, A., Anguelov, D., Flynn, J., Kosecka, J.: 3D bounding box estimation using deep learning and geometry. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7074\u20137082 (2017)","DOI":"10.1109\/CVPR.2017.597"},{"key":"1_CR28","doi-asserted-by":"crossref","unstructured":"Nicolas, C., Francisco, M., Gabriel, S., Nicolas, U., Alexander, K., Sergey, Z.: End-to-end object detection with transformers. In: ECCV, pp. 213\u2013229 (2020)","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"1_CR29","doi-asserted-by":"crossref","unstructured":"Pang, J., Chen, K., Shi, J., Feng, H., Ouyang, W., Lin, D.: Libra R-CNN: towards balanced learning for object detection. In: CVPR, pp. 821\u2013830 (2019)","DOI":"10.1109\/CVPR.2019.00091"},{"key":"1_CR30","unstructured":"Park, J., Xu, C., Yang, S., Keutzer, K., Kitani, K., Tomizuka, M., Zhan, W.: Time will tell: new outlooks and a baseline for temporal multi-view 3D object detection. In: ICLR (2023)"},{"key":"1_CR31","doi-asserted-by":"crossref","unstructured":"Philion, J., Fidler, S.: Lift, splat, shoot: encoding images from arbitrary camera rigs by implicitly unprojecting to 3D. In: ECCV, pp. 194\u2013210 (2020)","DOI":"10.1007\/978-3-030-58568-6_12"},{"key":"1_CR32","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: CVPR, pp. 779\u2013788 (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"1_CR33","doi-asserted-by":"crossref","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. IEEE TPAMI, 1137\u20131149 (2017)","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"1_CR34","unstructured":"Roh, B., Shin, J., Shin, W., Kim, S.: Sparse DETR: efficient end-to-end object detection with learnable sparsity. In: ICLR (2021)"},{"key":"1_CR35","doi-asserted-by":"crossref","unstructured":"Tian, Z., Shen, C., Chen, H., He, T.: FCOS: fully convolutional one-stage object detection. In: ICCV, pp. 9627\u20139636 (2019)","DOI":"10.1109\/ICCV.2019.00972"},{"key":"1_CR36","doi-asserted-by":"crossref","unstructured":"Wang, S., Jiang, X., Li, Y.: Focal-PETR: embracing foreground for efficient multi-camera 3D object detection. IEEE Trans. Intell. Veh. (2023)","DOI":"10.1109\/TIV.2023.3332608"},{"key":"1_CR37","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. In: ICCV, pp. 3621\u20133631 (2023)","DOI":"10.1109\/ICCV51070.2023.00335"},{"key":"1_CR38","doi-asserted-by":"crossref","unstructured":"Wang, T., Zhu, X., Pang, J., Lin, D.: FCOS3D: fully convolutional one-stage monocular 3D object detection. In: ICCV, pp. 913\u2013922 (2021)","DOI":"10.1109\/ICCVW54120.2021.00107"},{"key":"1_CR39","unstructured":"Wang, Y., Guizilini, V., Zhang, T., Wang, Y., Zhao, H., Solomon, J.: DETR3D: 3D object detection from multi-view images via 3D-to-2D queries. In: COLR, pp. 180\u2013191 (2021)"},{"key":"1_CR40","doi-asserted-by":"crossref","unstructured":"Wang, Z., Huang, Z., Fu, J., Wang, N., Liu, S.: Object as query: equipping any 2D object detector with 3D detection ability. In: ICCV, pp. 3791\u20133800 (2023)","DOI":"10.1109\/ICCV51070.2023.00351"},{"key":"1_CR41","doi-asserted-by":"crossref","unstructured":"Yang, C., et al.: BEVFormer v2: adapting modern image backbones to bird\u2019s-eye-view recognition via perspective supervision. In: CVPR, pp. 17830\u201317839 (2023)","DOI":"10.1109\/CVPR52729.2023.01710"},{"key":"1_CR42","unstructured":"Yao, J., Lai, Y.: DynamicBEV: leveraging dynamic queries and temporal context for 3D object detection. arXiv preprint arXiv:2310.05989 (2023)"},{"key":"1_CR43","unstructured":"Zhang, H., et al.: DINO: DETR with improved denoising anchor boxes for end-to-end object detection. In: ICLR (2022)"},{"key":"1_CR44","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)"},{"key":"1_CR45","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable DETR: deformable transformers for end-to-end object detection. In: ICLR (2020)"},{"key":"1_CR46","doi-asserted-by":"crossref","unstructured":"Zong, Z., Jiang, D., Song, G., Xue, Z., Su, J., Li, H., Liu, Y.: Temporal enhanced training of multi-view 3D object detector via historical object prediction. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00350"},{"key":"1_CR47","doi-asserted-by":"crossref","unstructured":"Zong, Z., Song, G., Liu, Y.: DETRs with collaborative hybrid assignments training. In: ICCV, pp. 6748\u20136758 (2023)","DOI":"10.1109\/ICCV51070.2023.00621"}],"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\/978-3-031-72627-9_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,19]],"date-time":"2024-10-19T21:03:17Z","timestamp":1729371797000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72627-9_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,20]]},"ISBN":["9783031726262","9783031726279"],"references-count":47,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72627-9_1","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,20]]},"assertion":[{"value":"20 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"}}]}}