{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T18:40:28Z","timestamp":1776883228408,"version":"3.51.2"},"publisher-location":"Cham","reference-count":48,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030660956","type":"print"},{"value":"9783030660963","type":"electronic"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"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":[[2020]]},"DOI":"10.1007\/978-3-030-66096-3_42","type":"book-chapter","created":{"date-parts":[[2021,1,2]],"date-time":"2021-01-02T07:03:14Z","timestamp":1609570994000},"page":"631-647","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Semi-supervised Viewpoint Estimation with Geometry-Aware Conditional Generation"],"prefix":"10.1007","author":[{"given":"Octave","family":"Mariotti","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6947-6918","authenticated-orcid":false,"given":"Hakan","family":"Bilen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,1,3]]},"reference":[{"key":"42_CR1","unstructured":"Berthelot, D., Carlini, N., Goodfellow, I., Papernot, N., Oliver, A., Raffel, C.: MixMatch: a holistic approach to semi-supervised learning. arXiv:1905.02249 (2019)"},{"key":"42_CR2","unstructured":"Chang, A.X., et al.: ShapeNet: an information-rich 3D model repository. arXiv preprint arXiv:1512.03012 (2015)"},{"key":"42_CR3","unstructured":"Cohen, T.S., Geiger, M., K\u00f6hler, J., Welling, M.: Spherical CNNs. In: Proceedings of the International Conference on Learning Representations (ICLR) (2018)"},{"key":"42_CR4","unstructured":"Esteves, C., Allen-Blanchette, C., Makadia, A., Daniilidis, K.: 3D object classification and retrieval with spherical CNNs. arXiv preprint arXiv:1711.06721 (2017)"},{"key":"42_CR5","unstructured":"Esteves, C., Sud, A., Luo, Z., Daniilidis, K., Makadia, A.: Cross-domain 3D equivariant image embeddings. arXiv preprint arXiv:1812.02716 (2018)"},{"key":"42_CR6","doi-asserted-by":"crossref","unstructured":"Georgakis, G., Reza, M.A., Mousavian, A., Le, P.H., Ko\u0161eck\u00e1, J.: Multiview RGB-D dataset for object instance detection. In: 2016 Fourth International Conference on 3D Vision (3DV), pp. 426\u2013434. IEEE (2016)","DOI":"10.1109\/3DV.2016.52"},{"key":"42_CR7","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1440\u20131448 (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"42_CR8","doi-asserted-by":"crossref","unstructured":"Grabner, A., Roth, P.M., Lepetit, V.: 3D pose estimation and 3D model retrieval for objects in the wild. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3022\u20133031 (2018)","DOI":"10.1109\/CVPR.2018.00319"},{"key":"42_CR9","doi-asserted-by":"crossref","unstructured":"Hinterstoisser, S., et al.: Multimodal templates for real-time detection of texture-less objects in heavily cluttered scenes. In: International Conference on Computer Vision, pp. 858\u2013865. IEEE (2011)","DOI":"10.1109\/ICCV.2011.6126326"},{"key":"42_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"548","DOI":"10.1007\/978-3-642-37331-2_42","volume-title":"Computer Vision \u2013 ACCV 2012","author":"S Hinterstoisser","year":"2013","unstructured":"Hinterstoisser, S., et al.: Model based training, detection and pose estimation of texture-less 3D objects in heavily cluttered scenes. In: Lee, K.M., Matsushita, Y., Rehg, J.M., Hu, Z. (eds.) ACCV 2012. LNCS, vol. 7724, pp. 548\u2013562. Springer, Heidelberg (2013). https:\/\/doi.org\/10.1007\/978-3-642-37331-2_42"},{"key":"42_CR11","doi-asserted-by":"crossref","unstructured":"Hodan, T., Haluza, P., Obdr\u017e\u00e1lek, \u0160., Matas, J., Lourakis, M., Zabulis, X.: T-LESS: an RGB-D dataset for 6D pose estimation of texture-less objects. In: 2017 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 880\u2013888. IEEE (2017)","DOI":"10.1109\/WACV.2017.103"},{"key":"42_CR12","unstructured":"Insafutdinov, E., Dosovitskiy, A.: Unsupervised learning of shape and pose with differentiable point clouds. In: Advances in Neural Information Processing Systems, pp. 2802\u20132812 (2018)"},{"key":"42_CR13","unstructured":"Jaderberg, M., Simonyan, K., Zisserman, A., et al.: Spatial transformer networks. In: Advances in Neural Information Processing Systems, pp. 2017\u20132025 (2015)"},{"key":"42_CR14","unstructured":"Jakab, T., Gupta, A., Bilen, H., Vedaldi, A.: Conditional image generation for learning the structure of visual objects. Methods 43, 44 (2018)"},{"key":"42_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"694","DOI":"10.1007\/978-3-319-46475-6_43","volume-title":"Computer Vision \u2013 ECCV 2016","author":"J Johnson","year":"2016","unstructured":"Johnson, J., Alahi, A., Fei-Fei, L.: Perceptual losses for real-time style transfer and super-resolution. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 694\u2013711. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46475-6_43"},{"key":"42_CR16","doi-asserted-by":"crossref","unstructured":"Joung, S., et al.: Cylindrical convolutional networks for joint object detection and viewpoint estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14163\u201314172 (2020)","DOI":"10.1109\/CVPR42600.2020.01417"},{"key":"42_CR17","doi-asserted-by":"crossref","unstructured":"Kanazawa, A., Tulsiani, S., Efros, A.A., Malik, J.: Learning category-specific mesh reconstruction from image collections. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 371\u2013386 (2018)","DOI":"10.1007\/978-3-030-01267-0_23"},{"key":"42_CR18","doi-asserted-by":"crossref","unstructured":"Kanezaki, A., Matsushita, Y., Nishida, Y.: RotationNet: joint object categorization and pose estimation using multiviews from unsupervised viewpoints. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5010\u20135019 (2018)","DOI":"10.1109\/CVPR.2018.00526"},{"key":"42_CR19","doi-asserted-by":"crossref","unstructured":"Kato, H., Ushiku, Y., Harada, T.: Neural 3D mesh renderer. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3907\u20133916 (2018)","DOI":"10.1109\/CVPR.2018.00411"},{"key":"42_CR20","doi-asserted-by":"crossref","unstructured":"Kehl, W., Manhardt, F., Tombari, F., Ilic, S., Navab, N.: SSD-6D: making RGB-based 3D detection and 6D pose estimation great again. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1521\u20131529 (2017)","DOI":"10.1109\/ICCV.2017.169"},{"key":"42_CR21","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"42_CR22","unstructured":"Kulkarni, T.D., Whitney, W.F., Kohli, P., Tenenbaum, J.: Deep convolutional inverse graphics network. In: Advances in Neural Information Processing Systems, pp. 2539\u20132547 (2015)"},{"key":"42_CR23","doi-asserted-by":"crossref","unstructured":"Liao, S., Gavves, E., Snoek, C.G.: Spherical regression: learning viewpoints, surface normals and 3D rotations on n-spheres. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 9759\u20139767 (2019)","DOI":"10.1109\/CVPR.2019.00999"},{"key":"42_CR24","doi-asserted-by":"crossref","unstructured":"Liebelt, J., Schmid, C.: Multi-view object class detection with a 3D geometric model. In: 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 1688\u20131695. IEEE (2010)","DOI":"10.1109\/CVPR.2010.5539836"},{"key":"42_CR25","doi-asserted-by":"crossref","unstructured":"Mahendran, S., Ali, H., Vidal, R.: 3D pose regression using convolutional neural networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2174\u20132182 (2017)","DOI":"10.1109\/ICCVW.2017.254"},{"key":"42_CR26","doi-asserted-by":"crossref","unstructured":"Mustikovela, S.K., et al.: Self-supervised viewpoint learning from image collections. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3971\u20133981 (2020)","DOI":"10.1109\/CVPR42600.2020.00403"},{"key":"42_CR27","doi-asserted-by":"crossref","unstructured":"Nguyen-Phuoc, T., Li, C., Theis, L., Richardt, C., Yang, Y.L.: HoloGAN: unsupervised learning of 3D representations from natural images. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 7588\u20137597 (2019)","DOI":"10.1109\/ICCV.2019.00768"},{"key":"42_CR28","doi-asserted-by":"crossref","unstructured":"Rad, M., Lepetit, V.: BB8: a scalable, accurate, robust to partial occlusion method for predicting the 3D poses of challenging objects without using depth. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3828\u20133836 (2017)","DOI":"10.1109\/ICCV.2017.413"},{"key":"42_CR29","doi-asserted-by":"crossref","unstructured":"Rhodin, H., Salzmann, M., Fua, P.: Unsupervised geometry-aware representation for 3D human pose estimation. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 750\u2013767 (2018)","DOI":"10.1007\/978-3-030-01249-6_46"},{"key":"42_CR30","doi-asserted-by":"crossref","unstructured":"Su, H., Qi, C.R., Li, Y., Guibas, L.J.: Render for CNN: viewpoint estimation in images using CNNs trained with rendered 3D model views. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2686\u20132694 (2015)","DOI":"10.1109\/ICCV.2015.308"},{"key":"42_CR31","doi-asserted-by":"crossref","unstructured":"Sundermeyer, M., Marton, Z.C., Durner, M., Brucker, M., Triebel, R.: Implicit 3D orientation learning for 6D object detection from RGB images. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 699\u2013715 (2018)","DOI":"10.1007\/978-3-030-01231-1_43"},{"key":"42_CR32","unstructured":"Suwajanakorn, S., Snavely, N., Tompson, J.J., Norouzi, M.: Discovery of latent 3D keypoints via end-to-end geometric reasoning. In: Advances in Neural Information Processing Systems, pp. 2059\u20132070 (2018)"},{"key":"42_CR33","doi-asserted-by":"crossref","unstructured":"Tan, V., Budvytis, I., Cipolla, R.: Indirect deep structured learning for 3D human body shape and pose prediction. In: British Machine Vision Conference (BMVC) (2018)","DOI":"10.5244\/C.31.15"},{"key":"42_CR34","unstructured":"Tarvainen, A., Valpola, H.: Mean teachers are better role models: weight-averaged consistency targets improve semi-supervised deep learning results. In: Advances in Neural Information Processing Systems, pp. 1195\u20131204 (2017)"},{"key":"42_CR35","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":"42_CR36","unstructured":"Thewlis, J., Bilen, H., Vedaldi, A.: Unsupervised learning of object frames by dense equivariant image labelling. In: Advances in Neural Information Processing Systems, pp. 844\u2013855 (2017)"},{"key":"42_CR37","doi-asserted-by":"crossref","unstructured":"Thewlis, J., Bilen, H., Vedaldi, A.: Unsupervised learning of object landmarks by factorized spatial embeddings. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5916\u20135925 (2017)","DOI":"10.1109\/ICCV.2017.348"},{"key":"42_CR38","unstructured":"Thewlis, J., Bilen, H., Vedaldi, A.: Modelling and unsupervised learning of symmetric deformable object categories. In: Advances in Neural Information Processing Systems, pp. 8178\u20138189 (2018)"},{"key":"42_CR39","doi-asserted-by":"crossref","unstructured":"Tobin, J., Fong, R., Ray, A., Schneider, J., Zaremba, W., Abbeel, P.: Domain randomization for transferring deep neural networks from simulation to the real world. In: 2017 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 23\u201330. IEEE (2017)","DOI":"10.1109\/IROS.2017.8202133"},{"key":"42_CR40","doi-asserted-by":"crossref","unstructured":"Tulsiani, S., Efros, A.A., Malik, J.: Multi-view consistency as supervisory signal for learning shape and pose prediction. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2897\u20132905 (2018)","DOI":"10.1109\/CVPR.2018.00306"},{"key":"42_CR41","doi-asserted-by":"crossref","unstructured":"Tulsiani, S., Malik, J.: Viewpoints and keypoints. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1510\u20131519 (2015)","DOI":"10.1109\/CVPR.2015.7298758"},{"key":"42_CR42","doi-asserted-by":"crossref","unstructured":"Worrall, D.E., Garbin, S.J., Turmukhambetov, D., Brostow, G.J.: Interpretable transformations with encoder-decoder networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5726\u20135735 (2017)","DOI":"10.1109\/ICCV.2017.611"},{"key":"42_CR43","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":"42_CR44","unstructured":"Xie, Q., Dai, Z., Hovy, E., Luong, M.T., Le, Q.V.: Unsupervised data augmentation for consistency training. arXiv preprint arXiv:1904.12848 (2019)"},{"key":"42_CR45","unstructured":"Yan, X., Yang, J., Yumer, E., Guo, Y., Lee, H.: Perspective transformer nets: learning single-view 3D object reconstruction without 3D supervision. In: Advances in Neural Information Processing Systems, pp. 1696\u20131704 (2016)"},{"key":"42_CR46","doi-asserted-by":"crossref","unstructured":"Yang, G., Cui, Y., Belongie, S., Hariharan, B.: Learning single-view 3D reconstruction with limited pose supervision. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 86\u2013101 (2018)","DOI":"10.1007\/978-3-030-01267-0_6"},{"key":"42_CR47","unstructured":"Zhang, H., Cisse, M., Dauphin, Y.N., Lopez-Paz, D.: mixup: beyond empirical risk minimization. In: International Conference on Machine Learning (2018)"},{"key":"42_CR48","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 2020 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-66096-3_42","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,2]],"date-time":"2025-01-02T00:16:01Z","timestamp":1735776961000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-66096-3_42"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030660956","9783030660963"],"references-count":48,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-66096-3_42","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"3 January 2021","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":"Glasgow","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 August 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2020.eu\/","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":"OpenReview","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5025","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":"1360","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":"27% - 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","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":"7","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)"}},{"value":"The conference was held virtually due to the COVID-19 pandemic. From the ECCV Workshops 249 full papers, 18 short papers, and 21 further contributions were published out of a total of 467 submissions.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}