{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T16:43:52Z","timestamp":1777567432019,"version":"3.51.4"},"publisher-location":"Singapore","reference-count":36,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819785070","type":"print"},{"value":"9789819785087","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"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\/978-981-97-8508-7_4","type":"book-chapter","created":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T06:09:24Z","timestamp":1730527764000},"page":"46-63","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["3D Data Augmentation for Driving Scenes on Camera"],"prefix":"10.1007","author":[{"given":"Wenwen","family":"Tong","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiangwei","family":"Xie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianyu","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hanming","family":"Deng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Dai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lewei","family":"Lu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junchi","family":"Yan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongyang","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,3]]},"reference":[{"key":"4_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":"4_CR2","doi-asserted-by":"crossref","unstructured":"Caesar, H., Bankiti, V., Lang, A.H., Vora, S., Liong, V.E., Xu, Q., Krishnan, A., Pan, Y., Baldan, G., Beijbom, O.: nuscenes: a multimodal dataset for autonomous driving. In: CVPR, pp. 11621\u201311631 (2020)","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"4_CR3","doi-asserted-by":"crossref","unstructured":"Choi, J., Song, Y., Kwak, N.: Part-aware data augmentation for 3d object detection in point cloud. In: IROS, pp. 3391\u20133397 (2021)","DOI":"10.1109\/IROS51168.2021.9635887"},{"key":"4_CR4","unstructured":"Cubuk, E.D., Zoph, B., Man\u00e9, D., Vasudevan, V., Le, Q.V.: Autoaugment: learning augmentation policies from data (2018). http:\/\/arxiv.org\/abs\/1805.09501"},{"key":"4_CR5","doi-asserted-by":"crossref","unstructured":"Deng, K., Liu, A., Zhu, J.Y., Ramanan, D.: Depth-supervised nerf: fewer views and faster training for free. In: CVPR, pp. 12882\u201312891 (2022)","DOI":"10.1109\/CVPR52688.2022.01254"},{"key":"4_CR6","unstructured":"Dosovitskiy, A., Ros, G., Codevilla, F., Lopez, A., Koltun, V.: CARLA: an open urban driving simulator. In: CORL, pp. 1\u201316 (2017)"},{"key":"4_CR7","doi-asserted-by":"crossref","unstructured":"Fang, J., Zuo, X., Zhou, D., Jin, S., Wang, S., Zhang, L.: Lidar-aug: a general rendering-based augmentation framework for 3d object detection. In: CVPR, pp. 4710\u20134720 (2021)","DOI":"10.1109\/CVPR46437.2021.00468"},{"key":"4_CR8","doi-asserted-by":"crossref","unstructured":"Fridovich-Keil, S., Yu, A., Tancik, M., Chen, Q., Recht, B., Kanazawa, A.: Plenoxels: radiance fields without neural networks. In: CVPR, pp. 5501\u20135510 (2022)","DOI":"10.1109\/CVPR52688.2022.00542"},{"key":"4_CR9","doi-asserted-by":"crossref","unstructured":"Ghiasi, G., Cui, Y., Srinivas, A., Qian, R., Lin, T.Y., Cubuk, E.D., Le, Q.V., Zoph, B.: Simple copy-paste is a strong data augmentation method for instance segmentation. In: CVPR, pp. 2918\u20132928 (2021)","DOI":"10.1109\/CVPR46437.2021.00294"},{"key":"4_CR10","doi-asserted-by":"crossref","unstructured":"Guizilini, V., Ambrus, R., Pillai, S., Raventos, A., Gaidon, A.: 3d packing for self-supervised monocular depth estimation. In: CVPR, pp. 2485\u20132494 (2020)","DOI":"10.1109\/CVPR42600.2020.00256"},{"key":"4_CR11","unstructured":"Hung, W.C., Kretzschmar, H., Casser, V., Hwang, J.J., Anguelov, D.: Let-3d-ap: longitudinal error tolerant 3d average precision for camera-only 3d detection (2022). arXiv:2206.07705"},{"key":"4_CR12","unstructured":"Hung, W.C., Kretzschmar, H., Casser, V., Hwang, J.J., Anguelov, D.: Let-3d-ap: longitudinal error tolerant 3d average precision for camera-only 3d detection (2022). arXiv:2206.07705"},{"key":"4_CR13","doi-asserted-by":"crossref","unstructured":"Kundu, A., Genova, K., Yin, X., Fathi, A., Pantofaru, C., Guibas, L.J., Tagliasacchi, A., Dellaert, F., Funkhouser, T.A.: Panoptic neural fields: a semantic object-aware neural scene representation. In: CVPR, pp. 12861\u201312871 (2022)","DOI":"10.1109\/CVPR52688.2022.01253"},{"key":"4_CR14","unstructured":"Li, H., Li, Y., Wang, H., Zeng, J., Xu, H., Cai, P., Chen, L., Yan, J., Xu, F., Xiong, L., Wang, J., Zhu, F., Yan, K., Xu, C., Wang, T., Xia, F., Mu, B., Peng, Z., Lin, D., Qiao, Y.: Open-sourced data ecosystem in autonomous driving: the present and future (2024)"},{"key":"4_CR15","doi-asserted-by":"publisher","unstructured":"Li, H., Sima, C., Dai, J., Wang, W., Lu, L., Wang, H., Zeng, J., Li, Z., Yang, J., Deng, H., Tian, H., Xie, E., Xie, J., Chen, L., Li, T., Li, Y., Gao, Y., Jia, X., Liu, S., Shi, J., Lin, D., Qiao, Y.: Delving into the devils of bird\u2019s-eye-view perception: a review, evaluation and recipe. In: IEEE Transactions on Pattern Analysis and Machine Intelligence, pp. 1\u201320 (2023). https:\/\/doi.org\/10.1109\/TPAMI.2023.3333838","DOI":"10.1109\/TPAMI.2023.3333838"},{"key":"4_CR16","doi-asserted-by":"crossref","unstructured":"Li, P., Zhao, H., Liu, P., Cao, F.: Rtm3d: real-time monocular 3d detection from object keypoints for autonomous driving. In: ECCV, pp. 644\u2013660. Springer (2020)","DOI":"10.1007\/978-3-030-58580-8_38"},{"key":"4_CR17","unstructured":"Li, Z., Li, L., Ma, Z., Zhang, P., Chen, J., Zhu, J.: Read: large-scale neural scene rendering for autonomous driving (2022). arXiv:2205.05509."},{"key":"4_CR18","doi-asserted-by":"crossref","unstructured":"Lian, Q., Ye, B., Xu, R., Yao, W., Zhang, T.: Exploring geometric consistency for monocular 3d object detection. In: CVPR, pp. 1685\u20131694 (2022),","DOI":"10.1109\/CVPR52688.2022.00173"},{"key":"4_CR19","doi-asserted-by":"crossref","unstructured":"Liu, Z., Wu, Z., T\u00f3th, R.: Smoke: single-stage monocular 3d object detection via keypoint estimation. In: CVPRW, pp. 996\u2013997 (2020),","DOI":"10.1109\/CVPRW50498.2020.00506"},{"key":"4_CR20","doi-asserted-by":"crossref","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. In: ECCV, pp. 99\u2013106 (2020)","DOI":"10.1145\/3503250"},{"key":"4_CR21","doi-asserted-by":"crossref","unstructured":"M\u00fcller, N., Simonelli, A., Porzi, L., Bul\u00f2, S.R., Nie\u00dfner, M., Kontschieder, P.: Autorf: learning 3d object radiance fields from single view observations. In: CVPR, pp. 3971\u20133980 (2022)","DOI":"10.1109\/CVPR52688.2022.00394"},{"key":"4_CR22","doi-asserted-by":"publisher","unstructured":"M\u00fcller, T., Evans, A., Schied, C., Keller, A.: Instant neural graphics primitives with a multiresolution hash encoding. ACM Trans. Graph. 41(4), 102, 1\u2013102:15 (2022). https:\/\/doi.org\/10.1145\/3528223.3530127, https:\/\/doi.org\/10.1145\/3528223.3530127","DOI":"10.1145\/3528223.3530127"},{"key":"4_CR23","doi-asserted-by":"crossref","unstructured":"Park, K., Sinha, U., Barron, J.T., Bouaziz, S., Goldman, D.B., Seitz, S.M., Martin-Brualla, R.: Nerfies: deformable neural radiance fields. In: ICCV, pp. 5865\u20135874 (2021)","DOI":"10.1109\/ICCV48922.2021.00581"},{"key":"4_CR24","doi-asserted-by":"crossref","unstructured":"Reuse, M., Simon, M., Sick, B.: About the ambiguity of data augmentation for 3d object detection in autonomous driving. In: ICCVW, pp. 979\u2013987 (2021)","DOI":"10.1109\/ICCVW54120.2021.00114"},{"key":"4_CR25","doi-asserted-by":"crossref","unstructured":"Schonberger, J.L., Frahm, J.M.: Structure-from-motion revisited. In: CVPR, pp. 4104\u20134113 (2016)","DOI":"10.1109\/CVPR.2016.445"},{"key":"4_CR26","doi-asserted-by":"crossref","unstructured":"Sun, C., Sun, M., Chen, H.T.: Direct voxel grid optimization: super-fast convergence for radiance fields reconstruction. In: CVPR, pp. 5459\u20135469 (2022)","DOI":"10.1109\/CVPR52688.2022.00538"},{"key":"4_CR27","doi-asserted-by":"crossref","unstructured":"Sun, P., Kretzschmar, H., Dotiwalla, X., Chouard, A., Patnaik, V., Tsui, P., Guo, J., Zhou, Y., Chai, Y., Caine, B., et\u00a0al.: Scalability in perception for autonomous driving: Waymo open dataset. In: CVPR, pp. 2446\u20132454 (2020)","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"4_CR28","doi-asserted-by":"crossref","unstructured":"Tancik, M., Casser, V., Yan, X., Pradhan, S., Mildenhall, B., Srinivasan, P.P., Barron, J.T., Kretzschmar, H.: Block-nerf: scalable large scene neural view synthesis. In: CVPR, pp. 8248\u20138258 (2022)","DOI":"10.1109\/CVPR52688.2022.00807"},{"key":"4_CR29","doi-asserted-by":"crossref","unstructured":"Wang, T., Zhu, X., Pang, J., Lin, D.: Fcos3d: fully convolutional one-stage monocular 3d object detection. In: CVPR (2021)","DOI":"10.1109\/ICCVW54120.2021.00107"},{"key":"4_CR30","doi-asserted-by":"crossref","unstructured":"Wang, X., Kong, T., Shen, C., Jiang, Y., Li, L.: Solo: segmenting objects by locations. In: ECCV, pp. 649\u2013665 (2020)","DOI":"10.1007\/978-3-030-58523-5_38"},{"key":"4_CR31","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: CoRL, pp. 180\u2013191. PMLR (2022)"},{"key":"4_CR32","doi-asserted-by":"crossref","unstructured":"Weng, X., Kitani, K.: Monocular 3d object detection with pseudo-lidar point cloud. In: ICCVW (2019)","DOI":"10.1109\/ICCVW.2019.00114"},{"key":"4_CR33","doi-asserted-by":"crossref","unstructured":"Yang, J., Gao, S., Qiu, Y., Chen, L., Li, T., Dai, B., Chitta, K., Wu, P., Zeng, J., Luo, P., et\u00a0al.: Generalized predictive model for autonomous driving (2024). arXiv:2403.09630","DOI":"10.1109\/CVPR52733.2024.01389"},{"key":"4_CR34","doi-asserted-by":"crossref","unstructured":"Yang, Z., Chen, L., Sun, Y., Li, H.: Visual point cloud forecasting enables scalable autonomous driving (2023). arXiv:2312.17655","DOI":"10.1109\/CVPR52733.2024.01390"},{"key":"4_CR35","unstructured":"Zhang, W., Wang, Z., Loy, C.C.: Exploring data augmentation for multi-modality 3d object detection (2020). arXiv:2012.12741"},{"key":"4_CR36","doi-asserted-by":"crossref","unstructured":"Zoph, B., Cubuk, E.D., Ghiasi, G., Lin, T.Y., Shlens, J., Le, Q.V.: Learning data augmentation strategies for object detection. In: ECCV, pp. 566\u2013583. Springer (2020)","DOI":"10.1007\/978-3-030-58583-9_34"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-8508-7_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T06:12:15Z","timestamp":1730527935000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-8508-7_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,3]]},"ISBN":["9789819785070","9789819785087"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-8508-7_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,3]]},"assertion":[{"value":"3 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Urumqi","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":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 October 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2024.prcv.cn\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}