{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T15:35:23Z","timestamp":1785512123449,"version":"3.56.0"},"publisher-location":"Cham","reference-count":42,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031727740","type":"print"},{"value":"9783031727757","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T00:00:00Z","timestamp":1727654400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T00:00:00Z","timestamp":1727654400000},"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\/978-3-031-72775-7_6","type":"book-chapter","created":{"date-parts":[[2024,9,29]],"date-time":"2024-09-29T07:01:50Z","timestamp":1727593310000},"page":"90-106","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":20,"title":["ViewFormer: Exploring Spatiotemporal Modeling for\u00a0Multi-view 3D Occupancy Perception via\u00a0View-Guided Transformers"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-1958-4205","authenticated-orcid":false,"given":"Jinke","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-6328-7552","authenticated-orcid":false,"given":"Xiao","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chonghua","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-3379-6685","authenticated-orcid":false,"given":"Xiaoqiang","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Wen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dan","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,9,30]]},"reference":[{"key":"6_CR1","unstructured":"Tesla AI Day (2021). https:\/\/www.youtube.com\/watch?v=j0z4FweCy4M"},{"key":"6_CR2","doi-asserted-by":"crossref","unstructured":"Baker, S., Scharstein, D., Lewis, J.P., Roth, S., Black, M.J., Szeliski, R.: A database and evaluation methodology for optical flow. In: ICCV, pp.\u00a01\u20138 (2007)","DOI":"10.1109\/ICCV.2007.4408903"},{"key":"6_CR3","doi-asserted-by":"crossref","unstructured":"Berman, M., Triki, A.R., Blaschko, M.B.: The Lov\u00e1sz-Softmax loss: a tractable surrogate for the optimization of the intersection-over-union measure in neural networks. In: CVPR, pp. 4413\u20134421 (2018)","DOI":"10.1109\/CVPR.2018.00464"},{"key":"6_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1007\/978-3-030-58592-1_9","volume-title":"Computer Vision \u2013 ECCV 2020","author":"G Brazil","year":"2020","unstructured":"Brazil, G., Pons-Moll, G., Liu, X., Schiele, B.: Kinematic 3D object detection in\u00a0monocular video. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12368, pp. 135\u2013152. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58592-1_9"},{"key":"6_CR5","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":"6_CR6","doi-asserted-by":"crossref","unstructured":"Cao, A.Q., de\u00a0Charette, R.: MonoScene: monocular 3D semantic scene completion. In: CVPR, pp. 3991\u20134001 (2022)","DOI":"10.1109\/CVPR52688.2022.00396"},{"key":"6_CR7","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 (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"6_CR8","unstructured":"Dezert, J., Moras, J., Pannetier, B.: Environment perception using grid occupancy estimation with belief functions. In: FUSION, pp. 1070\u20131077 (2015)"},{"key":"6_CR9","doi-asserted-by":"crossref","unstructured":"Fong, W.K., et al.: Panoptic nuScenes: a large-scale benchmark for LiDAR panoptic segmentation and tracking, pp. 3795\u20133802 (2022)","DOI":"10.1109\/LRA.2022.3148457"},{"key":"6_CR10","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"6_CR11","unstructured":"Huang, J., Huang, G.: BEVDet4D: exploit temporal cues in multi-camera 3D object detection. arXiv preprint arXiv:2203.17054 (2022)"},{"key":"6_CR12","unstructured":"Huang, J., Huang, G., Zhu, Z., Yun, Y., Du, D.: BEVDet: high-performance multi-camera 3D object detection in bird-eye-view. arXiv preprint arXiv:2112.11790 (2021)"},{"key":"6_CR13","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":"6_CR14","doi-asserted-by":"crossref","unstructured":"Lang, A.H., Vora, S., Caesar, H., Zhou, L., Yang, J., Beijbom, O.: PointPillars: fast encoders for object detection from point clouds. In: CVPR, pp. 12697\u201312705 (2019)","DOI":"10.1109\/CVPR.2019.01298"},{"key":"6_CR15","doi-asserted-by":"crossref","unstructured":"Li, J., He, X., Wen, Y., Gao, Y., Cheng, X., Zhang, D.: Panoptic-PHNet: towards real-time and high-precision LiDAR panoptic segmentation via clustering pseudo heatmap. In: CVPR, pp. 11799\u201311808 (2022)","DOI":"10.1109\/CVPR52688.2022.01151"},{"key":"6_CR16","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: VoxFormer: sparse voxel transformer for camera-based 3D semantic scene completion. arXiv preprint arXiv:2302.12251 (2023)","DOI":"10.1109\/CVPR52729.2023.00877"},{"key":"6_CR17","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: BEVDepth: acquisition of reliable depth for multi-view 3D object detection (2022). arXiv preprint arXiv:2206.10092","DOI":"10.1609\/aaai.v37i2.25233"},{"key":"6_CR18","doi-asserted-by":"publisher","unstructured":"Li, Z., et al.: BEVFormer: learning bird\u2019s-eye-view representation from multi-camera images via spatiotemporal transformers. In: Avidan, S., Brostow, G., Cisse, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision \u2013 ECCV 2022. LNCS, vol. 13669, pp. 1\u201318. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20077-9_1","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"6_CR19","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: ICCV, pp. 6919\u20136928 (2023)","DOI":"10.1109\/ICCV51070.2023.00637"},{"key":"6_CR20","unstructured":"Liao, B., et al.: MapTR: structured modeling and learning for online vectorized HD map construction. In: ICLR (2023)"},{"key":"6_CR21","doi-asserted-by":"crossref","unstructured":"Lin, T., Goyal, P., Girshick, R.B., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: ICCV, pp. 2999\u20133007 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"6_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","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.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"6_CR23","doi-asserted-by":"publisher","unstructured":"Liu, Y., Wang, T., Zhang, X., Sun, J.: PETR: position embedding transformation for multi-view 3D object detection. In: Avidan, S., Brostow, G., Cisse, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision \u2013 ECCV 2022. LNCS, vol. 13687, pp. 531\u2013548. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19812-0_31","DOI":"10.1007\/978-3-031-19812-0_31"},{"key":"6_CR24","doi-asserted-by":"crossref","unstructured":"Luo, W., Yang, B., Urtasun, R.: Fast and furious: real time end-to-end 3D detection, tracking and motion forecasting with a single convolutional net. In: CVPR, pp. 3569\u20133577 (2018)","DOI":"10.1109\/CVPR.2018.00376"},{"key":"6_CR25","unstructured":"Miao, R., et al.: OccDepth: a depth-aware method for 3D semantic scene completion. arXiv:2302.13540 (2023)"},{"key":"6_CR26","unstructured":"Park, J., et al.: Time will tell: new outlooks and a baseline for temporal multi-view 3D object detection. In: ICLR (2023)"},{"key":"6_CR27","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. LNCS, vol. 12359, pp. 194\u2013210. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58568-6_12"},{"key":"6_CR28","doi-asserted-by":"crossref","unstructured":"Qi, C.R., et al.: Offboard 3D object detection from point cloud sequences. In: CVPR, pp. 6134\u20136144 (2021)","DOI":"10.1109\/CVPR46437.2021.00607"},{"key":"6_CR29","doi-asserted-by":"crossref","unstructured":"Reading, C., Harakeh, A., Chae, J., Waslander, S.L.: Categorical depth distribution network for monocular 3D object detection. In: CVPR, pp. 8555\u20138564 (2021)","DOI":"10.1109\/CVPR46437.2021.00845"},{"key":"6_CR30","doi-asserted-by":"crossref","unstructured":"Schreiber, M., Belagiannis, V., Gl\u00e4ser, C., Dietmayer, K.: Dynamic occupancy grid mapping with recurrent neural networks. In: ICRA, pp. 6717\u20136724 (2021)","DOI":"10.1109\/ICRA48506.2021.9561375"},{"key":"6_CR31","unstructured":"Sima, C., et al.: Scene as occupancy. In: ICCV, pp. 8406\u20138415 (2023)"},{"key":"6_CR32","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: CVPR, pp. 1746\u20131754 (2017)","DOI":"10.1109\/CVPR.2017.28"},{"key":"6_CR33","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"402","DOI":"10.1007\/978-3-030-58536-5_24","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Z Teed","year":"2020","unstructured":"Teed, Z., Deng, J.: RAFT: recurrent all-pairs field transforms for optical flow. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12347, pp. 402\u2013419. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58536-5_24"},{"key":"6_CR34","unstructured":"Tian, X., Jiang, T., Yun, L., Wang, Y., Wang, Y., Zhao, H.: Occ3D: a large-scale 3D occupancy prediction benchmark for autonomous driving. arXiv preprint arXiv:2304.14365 (2023)"},{"key":"6_CR35","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. 11618\u201311628 (2023)","DOI":"10.1109\/ICCV51070.2023.00335"},{"key":"6_CR36","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":"6_CR37","doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: InternImage: exploring large-scale vision foundation models with deformable convolutions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 14408\u201314419, June 2023","DOI":"10.1109\/CVPR52729.2023.01385"},{"key":"6_CR38","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":"6_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: CoRL, pp. 180\u2013191 (2021)"},{"key":"6_CR40","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":"6_CR41","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":"6_CR42","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 (2021)"}],"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\/978-3-031-72775-7_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,29]],"date-time":"2024-09-29T07:37:24Z","timestamp":1727595444000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72775-7_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,30]]},"ISBN":["9783031727740","9783031727757"],"references-count":42,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72775-7_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9,30]]},"assertion":[{"value":"30 September 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"}}]}}