{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,24]],"date-time":"2026-01-24T17:04:33Z","timestamp":1769274273854,"version":"3.49.0"},"publisher-location":"Singapore","reference-count":49,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819984312","type":"print"},{"value":"9789819984329","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,12,24]],"date-time":"2023-12-24T00:00:00Z","timestamp":1703376000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,12,24]],"date-time":"2023-12-24T00:00:00Z","timestamp":1703376000000},"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":[[2024]]},"DOI":"10.1007\/978-981-99-8432-9_3","type":"book-chapter","created":{"date-parts":[[2023,12,23]],"date-time":"2023-12-23T08:02:17Z","timestamp":1703318537000},"page":"28-40","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Diffusion-Based 3D Object Detection with\u00a0Random Boxes"],"prefix":"10.1007","author":[{"given":"Xin","family":"Zhou","sequence":"first","affiliation":[]},{"given":"Jinghua","family":"Hou","sequence":"additional","affiliation":[]},{"given":"Tingting","family":"Yao","sequence":"additional","affiliation":[]},{"given":"Dingkang","family":"Liang","sequence":"additional","affiliation":[]},{"given":"Zhe","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Zhikang","family":"Zou","sequence":"additional","affiliation":[]},{"given":"Xiaoqing","family":"Ye","sequence":"additional","affiliation":[]},{"given":"Jianwei","family":"Cheng","sequence":"additional","affiliation":[]},{"given":"Xiang","family":"Bai","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,12,24]]},"reference":[{"key":"3_CR1","unstructured":"Amit, T., Nachmani, E., Shaharbany, T., Wolf, L.: Segdiff: image segmentation with diffusion probabilistic models. arXiv preprint arXiv:2112.00390 (2021)"},{"key":"3_CR2","doi-asserted-by":"crossref","unstructured":"Bai, X., et al.: Transfusion: robust lidar-camera fusion for 3d object detection with transformers. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00116"},{"key":"3_CR3","doi-asserted-by":"crossref","unstructured":"Brempong, E.A., Kornblith, S., Chen, T., Parmar, N., Minderer, M., Norouzi, M.: Denoising pretraining for semantic segmentation. In: CVPR (2022)","DOI":"10.1109\/CVPRW56347.2022.00462"},{"key":"3_CR4","doi-asserted-by":"publisher","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 213\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"3_CR5","doi-asserted-by":"crossref","unstructured":"Chen, S., Sun, P., Song, Y., Luo, P.: Diffusiondet: diffusion model for object detection. arXiv preprint arXiv:2211.09788 (2022)","DOI":"10.1109\/ICCV51070.2023.01816"},{"key":"3_CR6","doi-asserted-by":"crossref","unstructured":"Chen, T., Li, L., Saxena, S., Hinton, G., Fleet, D.J.: A generalist framework for panoptic segmentation of images and videos. arXiv preprint arXiv:2210.06366 (2022)","DOI":"10.1109\/ICCV51070.2023.00090"},{"key":"3_CR7","unstructured":"Chen, T., Zhang, R., Hinton, G.: Analog bits: generating discrete data using diffusion models with self-conditioning. arXiv preprint arXiv:2208.04202 (2022)"},{"key":"3_CR8","doi-asserted-by":"crossref","unstructured":"Chen, X., Ma, H., Wan, J., Li, B., Xia, T.: Multi-view 3d object detection network for autonomous driving. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.691"},{"key":"3_CR9","doi-asserted-by":"crossref","unstructured":"Chen, Y., Liu, J., Zhang, X., Qi, X., Jia, J.: Voxelnext: fully sparse voxelnet for 3d object detection and tracking. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.02076"},{"key":"3_CR10","doi-asserted-by":"crossref","unstructured":"Deng, J., Shi, S., Li, P., Zhou, W., Zhang, Y., Li, H.: Voxel r-cnn: towards high performance voxel-based 3d object detection. In: AAAI (2021)","DOI":"10.1609\/aaai.v35i2.16207"},{"key":"3_CR11","doi-asserted-by":"crossref","unstructured":"Duan, Y., Guo, X., Zhu, Z.: Diffusiondepth: diffusion denoising approach for monocular depth estimation. arXiv preprint arXiv:2303.05021 (2023)","DOI":"10.1007\/978-3-031-73247-8_25"},{"key":"3_CR12","doi-asserted-by":"crossref","unstructured":"Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? the kitti vision benchmark suite. In: CVPR (2012)","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"3_CR13","doi-asserted-by":"crossref","unstructured":"Gu, S., et al.: Vector quantized diffusion model for text-to-image synthesis. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01043"},{"key":"3_CR14","doi-asserted-by":"crossref","unstructured":"Han, J., Wan, Z., Liu, Z., Feng, J., Zhou, B.: Sparsedet: towards end-to-end 3d object detection. In: VISAPP (2022)","DOI":"10.5220\/0010918000003124"},{"key":"3_CR15","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: NeurIPS (2020)"},{"key":"3_CR16","doi-asserted-by":"publisher","unstructured":"Huang, T., Liu, Z., Chen, X., Bai, X.: EPNet: enhancing point features with image semantics for 3D object detection. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12360, pp. 35\u201352. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58555-6_3","DOI":"10.1007\/978-3-030-58555-6_3"},{"key":"3_CR17","doi-asserted-by":"crossref","unstructured":"Ji, Y., et al.: DDP: diffusion model for dense visual prediction. arXiv preprint arXiv:2303.17559 (2023)","DOI":"10.1109\/ICCV51070.2023.01987"},{"key":"3_CR18","doi-asserted-by":"crossref","unstructured":"Ku, J., Mozifian, M., Lee, J., Harakeh, A., Waslander, S.L.: Joint 3d proposal generation and object detection from view aggregation. In: IROS (2018)","DOI":"10.1109\/IROS.2018.8594049"},{"key":"3_CR19","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 (2019)","DOI":"10.1109\/CVPR.2019.01298"},{"key":"3_CR20","doi-asserted-by":"crossref","unstructured":"Li, J., Liu, Z., Hou, J., Liang, D.: Dds3d: dense pseudo-labels with dynamic threshold for semi-supervised 3d object detection. In: ICRA (2023)","DOI":"10.1109\/ICRA48891.2023.10160489"},{"key":"3_CR21","doi-asserted-by":"crossref","unstructured":"Li, X., et al.: Logonet: towards accurate 3d object detection with local-to-global cross-modal fusion. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01681"},{"key":"3_CR22","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: Bevdepth: acquisition of reliable depth for multi-view 3d object detection. In: AAAI (2023)","DOI":"10.1609\/aaai.v37i2.25233"},{"key":"3_CR23","doi-asserted-by":"publisher","unstructured":"Liang, M., Yang, B., Wang, S., Urtasun, R.: Deep continuous fusion for multi-sensor 3D object detection. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11220, pp. 663\u2013678. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01270-0_39","DOI":"10.1007\/978-3-030-01270-0_39"},{"key":"3_CR24","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"3_CR25","doi-asserted-by":"publisher","unstructured":"Liu, N., Li, S., Du, Y., Torralba, A., Tenenbaum, J.B.: Compositional visual generation with composable diffusion models. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13677, pp. 423\u2013439. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19790-1_26","DOI":"10.1007\/978-3-031-19790-1_26"},{"key":"3_CR26","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., 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","DOI":"10.1007\/978-3-031-19812-0_31"},{"key":"3_CR27","doi-asserted-by":"crossref","unstructured":"Liu, Z., Huang, T., Li, B., Chen, X., Wang, X., Bai, X.: Epnet++: cascade bi-directional fusion for multi-modal 3d object detection. IEEE Trans. Pattern Anal. Mach. Intell. (2022)","DOI":"10.1109\/TPAMI.2022.3228806"},{"key":"3_CR28","doi-asserted-by":"crossref","unstructured":"Liu, Z., Zhao, X., Huang, T., Hu, R., Zhou, Y., Bai, X.: Tanet: robust 3d object detection from point clouds with triple attention. In: AAAI (2020)","DOI":"10.1609\/aaai.v34i07.6837"},{"key":"3_CR29","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"3_CR30","doi-asserted-by":"crossref","unstructured":"Noh, J., Lee, S., Ham, B.: Hvpr: hybrid voxel-point representation for single-stage 3d object detection. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01437"},{"key":"3_CR31","doi-asserted-by":"crossref","unstructured":"Qi, C.R., Liu, W., Wu, C., Su, H., Guibas, L.J.: Frustum pointnets for 3d object detection from rgb-d data. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00102"},{"key":"3_CR32","unstructured":"Qi, C.R., Yi, L., Su, H., Guibas, L.J.: Pointnet++: Deep hierarchical feature learning on point sets in a metric space. In: NeurIPS (2017)"},{"key":"3_CR33","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"3_CR34","doi-asserted-by":"publisher","unstructured":"Shi, G., Li, R., Ma, C.: PillarNet: real-time and high-performance pillar-based 3D object detection. In: Avidan, S., et al. (eds.) ECCV 2022. LNCS, vol. 13670, pp. 35\u201352. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20080-9_3","DOI":"10.1007\/978-3-031-20080-9_3"},{"key":"3_CR35","doi-asserted-by":"crossref","unstructured":"Shi, S., et al.: Pv-rcnn: point-voxel feature set abstraction for 3d object detection. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01054"},{"key":"3_CR36","doi-asserted-by":"crossref","unstructured":"Shi, S., Wang, X., Li, H.: Pointrcnn: 3d object proposal generation and detection from point cloud. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00086"},{"key":"3_CR37","doi-asserted-by":"crossref","unstructured":"Shi, S., Wang, Z., Shi, J., Wang, X., Li, H.: From points to parts: 3D object detection from point cloud with part-aware and part-aggregation network. IEEE Trans. Pattern Anal. Mach. Intell. (2020)","DOI":"10.1109\/TPAMI.2020.2977026"},{"key":"3_CR38","doi-asserted-by":"crossref","unstructured":"Simonelli, A., Bulo, S.R., Porzi, L., L\u00f3pez-Antequera, M., Kontschieder, P.: Disentangling monocular 3d object detection. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00208"},{"key":"3_CR39","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. In: ICLR (2021)"},{"key":"3_CR40","doi-asserted-by":"crossref","unstructured":"Sun, P., et al.: Sparse r-cnn: end-to-end object detection with learnable proposals. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01422"},{"key":"3_CR41","doi-asserted-by":"crossref","unstructured":"Xiong, K., et al.: Cape: camera view position embedding for multi-view 3d object detection. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.02066"},{"key":"3_CR42","doi-asserted-by":"crossref","unstructured":"Yan, Y., Mao, Y., Li, B.: Second: sparsely embedded convolutional detection. Sensors (2018)","DOI":"10.3390\/s18103337"},{"key":"3_CR43","doi-asserted-by":"crossref","unstructured":"Yang, Z., Sun, Y., Liu, S., Jia, J.: 3dssd: point-based 3d single stage object detector. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01105"},{"key":"3_CR44","doi-asserted-by":"crossref","unstructured":"Yin, T., Zhou, X., Krahenbuhl, P.: Center-based 3d object detection and tracking. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01161"},{"key":"3_CR45","doi-asserted-by":"crossref","unstructured":"Zhang, D., et al.: Sam3d: zero-shot 3d object detection via segment anything model. arXiv preprint arXiv:2306.02245 (2023)","DOI":"10.1007\/s11432-023-3943-6"},{"key":"3_CR46","doi-asserted-by":"crossref","unstructured":"Zhang, D., et al.: A simple vision transformer for weakly semi-supervised 3d object detection. In: ICCV (2023)","DOI":"10.1109\/ICIP49359.2023.10222508"},{"key":"3_CR47","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Hu, Q., Xu, G., Ma, Y., Wan, J., Guo, Y.: Not all points are equal: learning highly efficient point-based detectors for 3d lidar point clouds. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01838"},{"key":"3_CR48","doi-asserted-by":"crossref","unstructured":"Zhou, D., et al.: Iou loss for 2d\/3d object detection. In: 3DV (2019)","DOI":"10.1109\/3DV.2019.00019"},{"key":"3_CR49","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Tuzel, O.: Voxelnet: end-to-end learning for point cloud based 3d object detection. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00472"}],"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\/978-981-99-8432-9_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,6]],"date-time":"2024-11-06T19:33:26Z","timestamp":1730921606000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-8432-9_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,24]]},"ISBN":["9789819984312","9789819984329"],"references-count":49,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-8432-9_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,12,24]]},"assertion":[{"value":"24 December 2023","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":"Xiamen","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":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 October 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 October 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/prcv2023.xmu.edu.cn\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1420","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"532","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"37% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3,78","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3,69","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}