{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T15:17:44Z","timestamp":1771514264444,"version":"3.50.1"},"publisher-location":"Cham","reference-count":38,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030586034","type":"print"},{"value":"9783030586041","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.springer.com\/tdm"},{"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.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-58604-1_6","type":"book-chapter","created":{"date-parts":[[2020,11,2]],"date-time":"2020-11-02T22:02:49Z","timestamp":1604354569000},"page":"87-103","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Novel View Synthesis on Unpaired Data by Conditional Deformable Variational Auto-Encoder"],"prefix":"10.1007","author":[{"given":"Mingyu","family":"Yin","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0950-4611","authenticated-orcid":false,"given":"Li","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5063-8801","authenticated-orcid":false,"given":"Qingli","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,11,3]]},"reference":[{"key":"6_CR1","doi-asserted-by":"crossref","unstructured":"Aubry, M., Maturana, D., Efros, A.A., Russell, B.C., Sivic, J.: Seeing 3D chairs: exemplar part-based 2D\u20133D alignment using a large dataset of cad models. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3762\u20133769 (2014)","DOI":"10.1109\/CVPR.2014.487"},{"key":"6_CR2","unstructured":"Avidan, S., Shashua, A.: Novel view synthesis in tensor space. In: Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 1034\u20131040. IEEE (1997)"},{"key":"6_CR3","doi-asserted-by":"crossref","unstructured":"Bao, J., Chen, D., Wen, F., Li, H., Hua, G.: cVAE-GAN: fine-grained image generation through asymmetric training. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2745\u20132754 (2017)","DOI":"10.1109\/ICCV.2017.299"},{"key":"6_CR4","doi-asserted-by":"crossref","unstructured":"Dai, J., et al.: Deformable convolutional networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 764\u2013773 (2017)","DOI":"10.1109\/ICCV.2017.89"},{"key":"6_CR5","doi-asserted-by":"crossref","unstructured":"Dosovitskiy, A., Tobias Springenberg, J., Brox, T.: Learning to generate chairs with convolutional neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1538\u20131546 (2015)","DOI":"10.1109\/CVPR.2015.7298761"},{"key":"6_CR6","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, pp. 2672\u20132680 (2014)"},{"issue":"5","key":"6_CR7","doi-asserted-by":"publisher","first-page":"807","DOI":"10.1016\/j.imavis.2009.08.002","volume":"28","author":"R Gross","year":"2010","unstructured":"Gross, R., Matthews, I., Cohn, J., Kanade, T., Baker, S.: Multi-pie. Image Vis. Comput. 28(5), 807\u2013813 (2010)","journal-title":"Image Vis. Comput."},{"key":"6_CR8","unstructured":"Gulrajani, I., Ahmed, F., Arjovsky, M., Dumoulin, V., Courville, A.C.: Improved training of Wasserstein GANs. In: Advances in Neural Information Processing Systems, pp. 5767\u20135777 (2017)"},{"key":"6_CR9","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: GANs trained by a two time-scale update rule converge to a local Nash equilibrium. In: Advances in Neural Information Processing Systems, pp. 6626\u20136637 (2017)"},{"issue":"5","key":"6_CR10","first-page":"6","volume":"2","author":"I Higgins","year":"2017","unstructured":"Higgins, I., et al.: beta-VAE: Learning basic visual concepts with a constrained variational framework. ICLR 2(5), 6 (2017)","journal-title":"ICLR"},{"key":"6_CR11","doi-asserted-by":"crossref","unstructured":"Huang, X., Belongie, S.: Arbitrary style transfer in real-time with adaptive instance normalization. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1501\u20131510 (2017)","DOI":"10.1109\/ICCV.2017.167"},{"key":"6_CR12","doi-asserted-by":"crossref","unstructured":"Isola, P., Zhu, J.-Y., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1125\u20131134 (2017)","DOI":"10.1109\/CVPR.2017.632"},{"issue":"4","key":"6_CR13","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2601097.2601209","volume":"33","author":"N Kholgade","year":"2014","unstructured":"Kholgade, N., Simon, T., Efros, A., Sheikh, Y.: 3D object manipulation in a single photograph using stock 3D models. ACM Trans. Graph. (TOG) 33(4), 1\u201312 (2014)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"6_CR14","unstructured":"Kingma, D.P., Adam, J.Ba.: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"6_CR15","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013)"},{"key":"6_CR16","unstructured":"Larsen, A.B.L., S\u00f8nderby, S.K., Larochelle, H., Winther, O.: Autoencoding beyond pixels using a learned similarity metric. arXiv preprint arXiv:1512.09300 (2015)"},{"key":"6_CR17","doi-asserted-by":"crossref","unstructured":"Massa, F., Russell, B.C., Aubry, M.: Deep exemplar 2D\u20133D detection by adapting from real to rendered views. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6024\u20136033 (2016)","DOI":"10.1109\/CVPR.2016.648"},{"key":"6_CR18","unstructured":"Mirza, M., Osindero, S.: Conditional generative adversarial nets. arXiv preprint arXiv:1411.1784 (2014)"},{"key":"6_CR19","unstructured":"Miyato, T., Kataoka, T., Koyama, M., Yoshida, Y.: Spectral normalization for generative adversarial networks. arXiv preprint arXiv:1802.05957 (2018)"},{"key":"6_CR20","unstructured":"Miyato, T., Koyama, M.: cGANs with projection discriminator. arXiv preprint arXiv:1802.05637 (2018)"},{"key":"6_CR21","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":"6_CR22","doi-asserted-by":"crossref","unstructured":"Park, E., Yang, J., Yumer, E., Ceylan, D., Berg, A.C.: Transformation-grounded image generation network for novel 3D view synthesis. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3500\u20133509 (2017)","DOI":"10.1109\/CVPR.2017.82"},{"key":"6_CR23","doi-asserted-by":"crossref","unstructured":"Park, T., Liu, M.-Y., Wang, T.-C., Zhu, J.-Y.: Semantic image synthesis with spatially-adaptive normalization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2337\u20132346 (2019)","DOI":"10.1109\/CVPR.2019.00244"},{"issue":"8","key":"6_CR24","doi-asserted-by":"publisher","first-page":"1576","DOI":"10.1109\/TPAMI.2016.2601093","volume":"39","author":"K Rematas","year":"2016","unstructured":"Rematas, K., Nguyen, C.H., Ritschel, T., Fritz, M., Tuytelaars, T.: Novel views of objects from a single image. IEEE Trans. Pattern Anal. Mach. Intell. 39(8), 1576\u20131590 (2016)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"6_CR25","doi-asserted-by":"crossref","unstructured":"Rematas, K., Ritschel, T., Fritz, M., Tuytelaars, T.: Image-based synthesis and re-synthesis of viewpoints guided by 3D models. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3898\u20133905 (2014)","DOI":"10.1109\/CVPR.2014.498"},{"key":"6_CR26","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"602","DOI":"10.1007\/978-3-540-88690-7_45","volume-title":"Computer Vision \u2013 ECCV 2008","author":"S Savarese","year":"2008","unstructured":"Savarese, S., Fei-Fei, L.: View synthesis for recognizing unseen poses of object classes. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008. LNCS, vol. 5304, pp. 602\u2013615. Springer, Heidelberg (2008). https:\/\/doi.org\/10.1007\/978-3-540-88690-7_45"},{"issue":"3972","key":"6_CR27","doi-asserted-by":"publisher","first-page":"701","DOI":"10.1126\/science.171.3972.701","volume":"171","author":"RN Shepard","year":"1971","unstructured":"Shepard, R.N., Metzler, J.: Mental rotation of three-dimensional objects. Science 171(3972), 701\u2013703 (1971)","journal-title":"Science"},{"key":"6_CR28","unstructured":"Sohn, K., Lee, H., Yan, X.: Learning structured output representation using deep conditional generative models. In: Advances in Neural Information Processing Systems, pp. 3483\u20133491 (2015)"},{"key":"6_CR29","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"162","DOI":"10.1007\/978-3-030-01219-9_10","volume-title":"Computer Vision \u2013 ECCV 2018","author":"S-H Sun","year":"2018","unstructured":"Sun, S.-H., Huh, M., Liao, Y.-H., Zhang, N., Lim, J.J.: Multi-view to novel view: synthesizing novel views with self-learned confidence. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11207, pp. 162\u2013178. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01219-9_10"},{"key":"6_CR30","doi-asserted-by":"crossref","unstructured":"Tian, Y., Peng, X., Zhao, L., Zhang, S., Metaxas, D.N.: CR-GAN: learning complete representations for multi-view generation. arXiv preprint arXiv:1806.11191 (2018)","DOI":"10.24963\/ijcai.2018\/131"},{"key":"6_CR31","doi-asserted-by":"crossref","unstructured":"Tran, L., Yin, X., Liu, X.: Disentangled representation learning GAN for pose-invariant face recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1415\u20131424 (2017)","DOI":"10.1109\/CVPR.2017.141"},{"key":"6_CR32","doi-asserted-by":"crossref","unstructured":"Wang, J., Nie, X., Xia, Y., Wu, Y., Zhu, S.-C.: Cross-view action modeling, learning and recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2649\u20132656 (2014)","DOI":"10.1109\/CVPR.2014.339"},{"issue":"4","key":"6_CR33","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1109\/TIP.2003.819861","volume":"13","author":"Z Wang","year":"2004","unstructured":"Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600\u2013612 (2004)","journal-title":"IEEE Trans. Image Process."},{"key":"6_CR34","doi-asserted-by":"crossref","unstructured":"Xu, X., Chen, Y.-C., Jia, J.: View independent generative adversarial network for novel view synthesis. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 7791\u20137800 (2019)","DOI":"10.1109\/ICCV.2019.00788"},{"key":"6_CR35","doi-asserted-by":"crossref","unstructured":"Zhang, C., Li, Z., Cheng, Y., Cai, R., Chao, H., Rui, Y.: Meshstereo: a global stereo model with mesh alignment regularization for view interpolation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2057\u20132065 (2015)","DOI":"10.1109\/ICCV.2015.238"},{"key":"6_CR36","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"286","DOI":"10.1007\/978-3-319-46493-0_18","volume-title":"Computer Vision \u2013 ECCV 2016","author":"T Zhou","year":"2016","unstructured":"Zhou, T., Tulsiani, S., Sun, W., Malik, J., Efros, A.A.: View synthesis by appearance flow. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 286\u2013301. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_18"},{"key":"6_CR37","doi-asserted-by":"crossref","unstructured":"Zhu, J.-Y., Park, T., Isola, P., Efros, A.A.: Unpaired image-to-image translation using cycle-consistent adversarial networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2223\u20132232 (2017)","DOI":"10.1109\/ICCV.2017.244"},{"key":"6_CR38","unstructured":"Zhu, J.-Y., et al.: Toward multimodal image-to-image translation. In: Advances in Neural Information Processing Systems, pp. 465\u2013476 (2017)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2020"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-58604-1_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T00:08:00Z","timestamp":1730506080000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58604-1_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030586034","9783030586041"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58604-1_6","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 November 2020","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.","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)"}}]}}