{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T16:11:51Z","timestamp":1778083911238,"version":"3.51.4"},"publisher-location":"Cham","reference-count":36,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031200854","type":"print"},{"value":"9783031200861","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-20086-1_13","type":"book-chapter","created":{"date-parts":[[2022,11,10]],"date-time":"2022-11-10T10:31:55Z","timestamp":1668076315000},"page":"220-236","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":35,"title":["Object Level Depth Reconstruction for\u00a0Category Level 6D Object Pose Estimation from\u00a0Monocular RGB Image"],"prefix":"10.1007","author":[{"given":"Zhaoxin","family":"Fan","sequence":"first","affiliation":[]},{"given":"Zhenbo","family":"Song","sequence":"additional","affiliation":[]},{"given":"Jian","family":"Xu","sequence":"additional","affiliation":[]},{"given":"Zhicheng","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Kejian","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Hongyan","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Jun","family":"He","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,11,11]]},"reference":[{"key":"13_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":"13_CR2","doi-asserted-by":"crossref","unstructured":"Chen, D., Li, J., Wang, Z., Xu, K.: Learning canonical shape space for category-level 6d object pose and size estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11973\u201311982 (2020)","DOI":"10.1109\/CVPR42600.2020.01199"},{"key":"13_CR3","doi-asserted-by":"crossref","unstructured":"Chen, W., Jia, X., Chang, H.J., Duan, J., Shen, L., Leonardis, A.: Fs-net: fast shape-based network for category-level 6d object pose estimation with decoupled rotation mechanism. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1581\u20131590 (2021)","DOI":"10.1109\/CVPR46437.2021.00163"},{"key":"13_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1007\/978-3-030-58574-7_9","volume-title":"Computer Vision \u2013 ECCV 2020","author":"X Chen","year":"2020","unstructured":"Chen, X., Dong, Z., Song, J., Geiger, A., Hilliges, O.: Category level object pose estimation via neural analysis-by-synthesis. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12371, pp. 139\u2013156. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58574-7_9"},{"key":"13_CR5","doi-asserted-by":"crossref","unstructured":"Du, G., Wang, K., Lian, S.: Vision-based robotic grasping from object localization, pose estimation, grasp detection to motion planning: a review. arXiv preprint arXiv:1905.06658 (2019)","DOI":"10.1007\/s10462-020-09888-5"},{"key":"13_CR6","unstructured":"Fan, Z., et al.: ACR-pose: adversarial canonical representation reconstruction network for category level 6d object pose estimation. arXiv preprint arXiv:2111.10524 (2021)"},{"key":"13_CR7","doi-asserted-by":"crossref","unstructured":"Fan, Z., Zhu, Y., He, Y., Sun, Q., Liu, H., He, J.: Deep learning on monocular object pose detection and tracking: a comprehensive overview. arXiv preprint arXiv:2105.14291 (2021)","DOI":"10.1145\/3524496"},{"key":"13_CR8","doi-asserted-by":"crossref","unstructured":"Gkioxari, G., Malik, J., Johnson, J.: Mesh R-CNN. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9785\u20139795 (2019)","DOI":"10.1109\/ICCV.2019.00988"},{"issue":"3","key":"13_CR9","doi-asserted-by":"publisher","first-page":"362","DOI":"10.1002\/rob.21918","volume":"37","author":"S Grigorescu","year":"2020","unstructured":"Grigorescu, S., Trasnea, B., Cocias, T., Macesanu, G.: A survey of deep learning techniques for autonomous driving. J. Field Robot. 37(3), 362\u2013386 (2020)","journal-title":"J. Field Robot."},{"key":"13_CR10","doi-asserted-by":"crossref","unstructured":"He, Y., Sun, W., Huang, H., Liu, J., Fan, H., Sun, J.: Pvn3d: a deep point-wise 3D keypoints voting network for 6DoF pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11632\u201311641 (2020)","DOI":"10.1109\/CVPR42600.2020.01165"},{"key":"13_CR11","doi-asserted-by":"crossref","unstructured":"Kendall, A., Grimes, M., Cipolla, R.: PoseNet: a convolutional network for real-time 6-DoF camera relocalization. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2938\u20132946 (2015)","DOI":"10.1109\/ICCV.2015.336"},{"key":"13_CR12","doi-asserted-by":"crossref","unstructured":"Ledig, C., et al.: Photo-realistic single image super-resolution using a generative adversarial network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4681\u20134690 (2017)","DOI":"10.1109\/CVPR.2017.19"},{"issue":"4","key":"13_CR13","doi-asserted-by":"publisher","first-page":"8575","DOI":"10.1109\/LRA.2021.3110538","volume":"6","author":"T Lee","year":"2021","unstructured":"Lee, T., Lee, B.U., Kim, M., Kweon, I.S.: Category-level metric scale object shape and pose estimation. IEEE Robot. Automa. Lett. 6(4), 8575\u20138582 (2021)","journal-title":"IEEE Robot. Automa. Lett."},{"issue":"2","key":"13_CR14","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1007\/s11263-008-0152-6","volume":"81","author":"V Lepetit","year":"2009","unstructured":"Lepetit, V., Moreno-Noguer, F., Fua, P.: EPnP: an accurate O (n) solution to the PnP problem. Int. J. Comput. Vis. 81(2), 155 (2009). https:\/\/doi.org\/10.1007\/s11263-008-0152-6","journal-title":"Int. J. Comput. Vis."},{"key":"13_CR15","doi-asserted-by":"crossref","unstructured":"Li, Y., Wang, G., Ji, X., Xiang, Y., Fox, D.: DeepIM: deep iterative matching for 6D pose estimation. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 683\u2013698 (2018)","DOI":"10.1007\/978-3-030-01231-1_42"},{"key":"13_CR16","doi-asserted-by":"crossref","unstructured":"Lin, J., Wei, Z., Li, Z., Xu, S., Jia, K., Li, Y.: DualPoseNet: category-level 6D object pose and size estimation using dual pose network with refined learning of pose consistency. arXiv preprint arXiv:2103.06526 (2021)","DOI":"10.1109\/ICCV48922.2021.00354"},{"key":"13_CR17","doi-asserted-by":"crossref","unstructured":"Peng, S., Liu, Y., Huang, Q., Zhou, X., Bao, H.: Pvnet: Pixel-wise voting network for 6dof pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 4561\u20134570 (2019)","DOI":"10.1109\/CVPR.2019.00469"},{"issue":"1","key":"13_CR18","doi-asserted-by":"publisher","first-page":"6","DOI":"10.3390\/computers7010006","volume":"7","author":"J Rambach","year":"2018","unstructured":"Rambach, J., Pagani, A., Schneider, M., Artemenko, O., Stricker, D.: 6DoF object tracking based on 3D scans for augmented reality remote live support. Computers 7(1), 6 (2018)","journal-title":"Computers"},{"key":"13_CR19","doi-asserted-by":"crossref","unstructured":"Song, C., Song, J., Huang, Q.: Hybridpose: 6D object pose estimation under hybrid representations. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 431\u2013440 (2020)","DOI":"10.1109\/CVPR42600.2020.00051"},{"key":"13_CR20","doi-asserted-by":"crossref","unstructured":"Song, Z., Lu, J., Zhang, T., Li, H.: End-to-end learning for inter-vehicle distance and relative velocity estimation in ADAS with a monocular camera. In: 2020 IEEE International Conference on Robotics and Automation (ICRA), pp. 11081\u201311087. IEEE (2020)","DOI":"10.1109\/ICRA40945.2020.9197557"},{"key":"13_CR21","doi-asserted-by":"crossref","unstructured":"Su, Y., Rambach, J., Minaskan, N., Lesur, P., Pagani, A., Stricker, D.: Deep multi-state object pose estimation for augmented reality assembly. In: 2019 IEEE International Symposium on Mixed and Augmented Reality Adjunct (ISMAR-Adjunct), pp. 222\u2013227. IEEE (2019)","DOI":"10.1109\/ISMAR-Adjunct.2019.00-42"},{"key":"13_CR22","doi-asserted-by":"crossref","unstructured":"Sun, P., et al.: Scalability in perception for autonomous driving: Waymo open dataset. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2446\u20132454 (2020)","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"13_CR23","unstructured":"Tan, D.J., Navab, N., Tombari, F.: 6D object pose estimation with depth images: a seamless approach for robotic interaction and augmented reality. arXiv preprint arXiv:1709.01459 (2017)"},{"key":"13_CR24","doi-asserted-by":"crossref","unstructured":"Tekin, B., Sinha, S.N., Fua, P.: Real-time seamless single shot 6D object pose prediction. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 292\u2013301 (2018)","DOI":"10.1109\/CVPR.2018.00038"},{"key":"13_CR25","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"530","DOI":"10.1007\/978-3-030-58589-1_32","volume-title":"Computer Vision \u2013 ECCV 2020","author":"M Tian","year":"2020","unstructured":"Tian, M., Ang, M.H., Lee, G.H.: Shape prior deformation for categorical 6D object pose and size estimation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12366, pp. 530\u2013546. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58589-1_32"},{"key":"13_CR26","unstructured":"Tremblay, J., To, T., Sundaralingam, B., Xiang, Y., Fox, D., Birchfield, S.: Deep object pose estimation for semantic robotic grasping of household objects. arXiv preprint arXiv:1809.10790 (2018)"},{"issue":"04","key":"13_CR27","doi-asserted-by":"publisher","first-page":"376","DOI":"10.1109\/34.88573","volume":"13","author":"S Umeyama","year":"1991","unstructured":"Umeyama, S.: Least-squares estimation of transformation parameters between two point patterns. IEEE Trans. Pattern Anal. Mach. Intell. 13(04), 376\u2013380 (1991)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"13_CR28","doi-asserted-by":"crossref","unstructured":"Wada, K., Sucar, E., James, S., Lenton, D., Davison, A.J.: MoreFusion: multi-object reasoning for 6D pose estimation from volumetric fusion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14540\u201314549 (2020)","DOI":"10.1109\/CVPR42600.2020.01455"},{"issue":"13","key":"13_CR29","doi-asserted-by":"publisher","first-page":"3707","DOI":"10.3390\/s20133707","volume":"20","author":"C Wang","year":"2020","unstructured":"Wang, C., et al.: Feature sensing and robotic grasping of objects with uncertain information: a review. Sensors 20(13), 3707 (2020)","journal-title":"Sensors"},{"key":"13_CR30","doi-asserted-by":"crossref","unstructured":"Wang, C., Xu, D., Zhu, Y., Mart\u00edn-Mart\u00edn, R., Lu, C., Fei-Fei, L., Savarese, S.: Densefusion: 6d object pose estimation by iterative dense fusion. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp. 3343\u20133352 (2019)","DOI":"10.1109\/CVPR.2019.00346"},{"key":"13_CR31","doi-asserted-by":"crossref","unstructured":"Wang, H., Sridhar, S., Huang, J., Valentin, J., Song, S., Guibas, L.J.: Normalized object coordinate space for category-level 6D object pose and size estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2642\u20132651 (2019)","DOI":"10.1109\/CVPR.2019.00275"},{"key":"13_CR32","doi-asserted-by":"crossref","unstructured":"Xiang, Y., Schmidt, T., Narayanan, V., Fox, D.: PoseCNN: a convolutional neural network for 6d object pose estimation in cluttered scenes. arXiv preprint arXiv:1711.00199 (2017)","DOI":"10.15607\/RSS.2018.XIV.019"},{"key":"13_CR33","doi-asserted-by":"crossref","unstructured":"Xu, R., Xiang, H., Tu, Z., Xia, X., Yang, M.H., Ma, J.: V2x-vit: vehicle-to-everything cooperative perception with vision transformer. arXiv preprint arXiv:2203.10638 (2022)","DOI":"10.1007\/978-3-031-19842-7_7"},{"key":"13_CR34","doi-asserted-by":"crossref","unstructured":"Xu, R., Xiang, H., Xia, X., Han, X., Liu, J., Ma, J.: Opv2v: an open benchmark dataset and fusion pipeline for perception with vehicle-to-vehicle communication. arXiv preprint arXiv:2109.07644 (2021)","DOI":"10.1109\/ICRA46639.2022.9812038"},{"key":"13_CR35","doi-asserted-by":"crossref","unstructured":"Zakharov, S., Shugurov, I., Ilic, S.: DPOD: 6D pose object detector and refiner. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1941\u20131950 (2019)","DOI":"10.1109\/ICCV.2019.00203"},{"key":"13_CR36","doi-asserted-by":"crossref","unstructured":"Zhao, Z., Wu, Z., Zhuang, Y., Li, B., Jia, J.: Tracking objects as pixel-wise distributions (2022)","DOI":"10.1007\/978-3-031-20047-2_5"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-20086-1_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,10]],"date-time":"2022-11-10T10:57:30Z","timestamp":1668077850000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20086-1_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031200854","9783031200861"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20086-1_13","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"11 November 2022","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":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","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":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","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":"1645","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":"28% - 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":"3.21","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":"3.91","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":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}