{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,23]],"date-time":"2026-01-23T12:53:30Z","timestamp":1769172810047,"version":"3.49.0"},"publisher-location":"Cham","reference-count":38,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031200762","type":"print"},{"value":"9783031200779","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\/978-3-031-20077-9_29","type":"book-chapter","created":{"date-parts":[[2022,11,5]],"date-time":"2022-11-05T16:21:52Z","timestamp":1667665312000},"page":"492-508","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["Robust Category-Level 6D Pose Estimation with\u00a0Coarse-to-Fine Rendering of\u00a0Neural Features"],"prefix":"10.1007","author":[{"given":"Wufei","family":"Ma","sequence":"first","affiliation":[]},{"given":"Angtian","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Alan","family":"Yuille","sequence":"additional","affiliation":[]},{"given":"Adam","family":"Kortylewski","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,11,6]]},"reference":[{"key":"29_CR1","unstructured":"Bai, Y., Wang, A., Kortylewski, A., Yuille, A.: CoKe: localized contrastive learning for robust keypoint detection. arXiv preprint arXiv:2009.14115 (2020)"},{"key":"29_CR2","doi-asserted-by":"publisher","unstructured":"Blanz, V., Vetter, T.: A morphable model for the synthesis of 3D faces. In: Proceedings of the 26th Annual Conference on Computer Graphics and Interactive Techniques, pp. 187\u2013194. SIGGRAPH 1999, ACM Press\/Addison-Wesley Publishing Co., USA (1999). https:\/\/doi.org\/10.1145\/311535.311556","DOI":"10.1145\/311535.311556"},{"key":"29_CR3","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":"29_CR4","doi-asserted-by":"crossref","unstructured":"Cimpoi, M., Maji, S., Kokkinos, I., Mohamed, S., Vedaldi, A.: Describing textures in the wild. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2014)","DOI":"10.1109\/CVPR.2014.461"},{"issue":"12","key":"29_CR5","doi-asserted-by":"publisher","first-page":"1269","DOI":"10.1007\/s11263-018-1064-8","volume":"126","author":"B Egger","year":"2018","unstructured":"Egger, B., et al.: Occlusion-aware 3D morphable models and an illumination prior for face image analysis. Int. J. Comput. Vis. 126(12), 1269\u20131287 (2018)","journal-title":"Int. J. Comput. Vis."},{"key":"29_CR6","unstructured":"Girshick, R., Felzenszwalb, P., McAllester, D.: Object detection with grammar models. In: Advances in Neural Information Processing Systems 24 (2011)"},{"key":"29_CR7","doi-asserted-by":"crossref","unstructured":"Grenander, U.: A unified approach to pattern analysis. In: Advances in computers, vol. 10, pp. 175\u2013216. Elsevier (1970)","DOI":"10.1016\/S0065-2458(08)60436-2"},{"key":"29_CR8","doi-asserted-by":"crossref","unstructured":"Grenander, U.: Elements of pattern theory. JHU Press, Baltimore (1996)","DOI":"10.56021\/9780801851872"},{"key":"29_CR9","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"29_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 (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.01165"},{"key":"29_CR11","unstructured":"Huber, P.J.: Robust statistics, vol. 523. Wiley (2004)"},{"key":"29_CR12","doi-asserted-by":"crossref","unstructured":"Iwase, S., Liu, X., Khirodkar, R., Yokota, R., Kitani, K.M.: Repose: fast 6D object pose refinement via deep texture rendering. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 3303\u20133312 (2021)","DOI":"10.1109\/ICCV48922.2021.00329"},{"key":"29_CR13","doi-asserted-by":"crossref","unstructured":"Kortylewski, A., He, J., Liu, Q., Cosgrove, C., Yang, C., Yuille, A.L.: Compositional generative networks and robustness to perceptible image changes. In: 2021 55th Annual Conference on Information Sciences and Systems (CISS), pp. 1\u20138. IEEE (2021)","DOI":"10.1109\/CISS50987.2021.9400221"},{"key":"29_CR14","doi-asserted-by":"crossref","unstructured":"Kortylewski, A., He, J., Liu, Q., Yuille, A.L.: Compositional convolutional neural networks: a deep architecture with innate robustness to partial occlusion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00896"},{"key":"29_CR15","doi-asserted-by":"crossref","unstructured":"Kortylewski, A., Liu, Q., Wang, A., Sun, Y., Yuille, A.: Compositional convolutional neural networks: a robust and interpretable model for object recognition under occlusion. International Journal of Computer Vision, pp. 1\u201325 (2020)","DOI":"10.1007\/s11263-020-01401-3"},{"key":"29_CR16","doi-asserted-by":"crossref","unstructured":"Kortylewski, A., Liu, Q., Wang, H., Zhang, Z., Yuille, A.: Combining compositional models and deep networks for robust object classification under occlusion. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 1333\u20131341 (2020)","DOI":"10.1109\/WACV45572.2020.9093560"},{"issue":"10","key":"29_CR17","first-page":"1995","volume":"3361","author":"Y LeCun","year":"1995","unstructured":"LeCun, Y., Bengio, Y., et al.: Convolutional networks for images, speech, and time series. Handb. Brain Theor. Neural Netw. 3361(10), 1995 (1995)","journal-title":"Handb. Brain Theor. Neural Netw."},{"key":"29_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"644","DOI":"10.1007\/978-3-030-58580-8_38","volume-title":"Computer Vision \u2013 ECCV 2020","author":"P Li","year":"2020","unstructured":"Li, P., Zhao, H., Liu, P., Cao, F.: RTM3D: real-time monocular 3D\u00a0detection from object keypoints for\u00a0autonomous driving. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12348, pp. 644\u2013660. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58580-8_38"},{"key":"29_CR19","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) (2018)","DOI":"10.1007\/978-3-030-01231-1_42"},{"key":"29_CR20","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. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 3560\u20133569 (2021)","DOI":"10.1109\/ICCV48922.2021.00354"},{"key":"29_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"170","DOI":"10.1007\/978-3-319-49409-8_16","volume-title":"Computer Vision \u2013 ECCV 2016 Workshops","author":"P Moreno","year":"2016","unstructured":"Moreno, P., Williams, C.K.I., Nash, C., Kohli, P.: Overcoming occlusion with inverse graphics. In: Hua, G., J\u00e9gou, H. (eds.) ECCV 2016. LNCS, vol. 9915, pp. 170\u2013185. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-49409-8_16"},{"key":"29_CR22","doi-asserted-by":"publisher","unstructured":"Pavlakos, G., Zhou, X., Chan, A., Derpanis, K.G., Daniilidis, K.: 6-DoF object pose from semantic keypoints. In: 2017 IEEE International Conference on Robotics and Automation (ICRA), pp. 2011\u20132018 (2017). https:\/\/doi.org\/10.1109\/ICRA.2017.7989233","DOI":"10.1109\/ICRA.2017.7989233"},{"key":"29_CR23","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 (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00469"},{"issue":"6","key":"29_CR24","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2016","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39(6), 1137\u20131149 (2016)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"29_CR25","doi-asserted-by":"crossref","unstructured":"Romaszko, L., Williams, C.K., Moreno, P., Kohli, P.: Vision-as-inverse-graphics: obtaining a rich 3D explanation of a scene from a single image. In: Proceedings of the IEEE International Conference on Computer Vision Workshops, pp. 851\u2013859 (2017)","DOI":"10.1109\/ICCVW.2017.115"},{"issue":"2","key":"29_CR26","doi-asserted-by":"publisher","first-page":"160","DOI":"10.1007\/s11263-016-0967-5","volume":"123","author":"S Sch\u00f6nborn","year":"2017","unstructured":"Sch\u00f6nborn, S., Egger, B., Morel-Forster, A., Vetter, T.: Markov Chain Monte Carlo for automated face image analysis. Int. J. Comput. Vis. 123(2), 160\u2013183 (2017)","journal-title":"Int. J. Comput. Vis."},{"issue":"04","key":"29_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":"29_CR28","unstructured":"Wang, A., Kortylewski, A., Yuille, A.: NEMO: Neural mesh models of contrastive features for robust 3D pose estimation. In: International Conference on Learning Representations (2021). https:\/\/openreview.net\/forum?id=pmj131uIL9H"},{"key":"29_CR29","first-page":"7207","volume":"34","author":"A Wang","year":"2021","unstructured":"Wang, A., Mei, S., Yuille, A.L., Kortylewski, A.: Neural view synthesis and matching for semi-supervised few-shot learning of 3D pose. Adv. Neural. Inf. Process. Syst. 34, 7207\u20137219 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"29_CR30","doi-asserted-by":"crossref","unstructured":"Wang, A., Sun, Y., Kortylewski, A., Yuille, A.L.: Robust object detection under occlusion with context-aware compositionalNets. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12645\u201312654 (2020)","DOI":"10.1109\/CVPR42600.2020.01266"},{"key":"29_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 (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00275"},{"key":"29_CR32","doi-asserted-by":"crossref","unstructured":"Wu, Z., Xiong, Y., Yu, S.X., Lin, D.: Unsupervised feature learning via non-parametric instance discrimination. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00393"},{"key":"29_CR33","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"160","DOI":"10.1007\/978-3-319-46484-8_10","volume-title":"Computer Vision \u2013 ECCV 2016","author":"Y Xiang","year":"2016","unstructured":"Xiang, Y., et al.: ObjectNet3D: a large scale database for 3D object recognition. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 160\u2013176. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46484-8_10"},{"key":"29_CR34","doi-asserted-by":"crossref","unstructured":"Xiang, Y., Mottaghi, R., Savarese, S.: Beyond pascal: a benchmark for 3D object detection in the wild. In: IEEE Winter Conference on Applications of Computer Vision, pp. 75\u201382. IEEE (2014)","DOI":"10.1109\/WACV.2014.6836101"},{"key":"29_CR35","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":"29_CR36","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"447","DOI":"10.1007\/978-3-030-66096-3_31","volume-title":"Computer Vision \u2013 ECCV 2020 Workshops","author":"M Xiao","year":"2020","unstructured":"Xiao, M., Kortylewski, A., Wu, R., Qiao, S., Shen, W., Yuille, A.: TDMPNet: prototype network with recurrent top-down modulation for robust object classification under partial occlusion. In: Bartoli, A., Fusiello, A. (eds.) ECCV 2020. LNCS, vol. 12536, pp. 447\u2013463. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-66096-3_31"},{"key":"29_CR37","doi-asserted-by":"crossref","unstructured":"Yuan, X., Kortylewski, A., Sun, Y., Yuille, A.: Robust instance segmentation through reasoning about multi-object occlusion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11141\u201311150 (2021)","DOI":"10.1109\/CVPR46437.2021.01099"},{"key":"29_CR38","doi-asserted-by":"crossref","unstructured":"Zhou, X., Karpur, A., Luo, L., Huang, Q.: StarMap for category-agnostic keypoint and viewpoint estimation. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 318\u2013334 (2018)","DOI":"10.1007\/978-3-030-01246-5_20"}],"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\/978-3-031-20077-9_29","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,11]],"date-time":"2023-03-11T06:52:34Z","timestamp":1678517554000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20077-9_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031200762","9783031200779"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20077-9_29","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":"6 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)"}}]}}