{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T08:21:35Z","timestamp":1743150095237,"version":"3.40.3"},"publisher-location":"Cham","reference-count":44,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030695378"},{"type":"electronic","value":"9783030695385"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-69538-5_42","type":"book-chapter","created":{"date-parts":[[2021,2,24]],"date-time":"2021-02-24T21:16:40Z","timestamp":1614201400000},"page":"695-711","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Sequential View Synthesis with Transformer"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9678-0886","authenticated-orcid":false,"given":"Phong","family":"Nguyen-Ha","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8311-1288","authenticated-orcid":false,"given":"Lam","family":"Huynh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8767-0864","authenticated-orcid":false,"given":"Esa","family":"Rahtu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0073-0866","authenticated-orcid":false,"given":"Janne","family":"Heikkil\u00e4","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,2,25]]},"reference":[{"key":"42_CR1","doi-asserted-by":"publisher","first-page":"39","DOI":"10.3724\/SP.J.2096-5796.2018.0004","volume":"1","author":"Y Chang","year":"2019","unstructured":"Chang, Y., Wang, G.P.: A review on image-based rendering. Virtual Reality Intell. Hardw. 1, 39\u201354 (2019)","journal-title":"Virtual Reality Intell. Hardw."},{"key":"42_CR2","doi-asserted-by":"publisher","first-page":"555","DOI":"10.1016\/j.image.2012.02.016","volume":"27","author":"M Tanimoto","year":"2012","unstructured":"Tanimoto, M.: FTV: free-viewpoint television. Sig. Process. Image Commun. 27, 555\u2013570 (2012)","journal-title":"Sig. Process. Image Commun."},{"key":"42_CR3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1117\/1.JEI.28.1.013049","volume":"28","author":"S Smirnov","year":"2019","unstructured":"Smirnov, S., Battisti, F., Gotchev, A.P.: Layered approach for improving the quality of free-viewpoint depth-image-based rendering images. J. Electron. Imaging 28, 1\u201317 (2019)","journal-title":"J. Electron. Imaging"},{"doi-asserted-by":"crossref","unstructured":"Joachimczak, M., Liu, J., Ando, H.: Real-time mixed-reality telepresence via 3D reconstruction with hololens and commodity depth sensors. In: Proceedings of the 19th ACM International Conference on Multimodal Interaction. ICMI 2017, pp. 514\u2013515. Association for Computing Machinery, New York (2017)","key":"42_CR4","DOI":"10.1145\/3136755.3143031"},{"doi-asserted-by":"crossref","unstructured":"Kolkmeier, J., Harmsen, E., Giesselink, S., Reidsma, D., Theune, M., Heylen, D.: With a little help from a holographic friend: the OpenIMPRESS mixed reality telepresence toolkit for remote collaboration systems. In: Proceedings of the 24th ACM Symposium on Virtual Reality Software and Technology. VRST 2018. Association for Computing Machinery, New York (2018)","key":"42_CR5","DOI":"10.1145\/3281505.3281542"},{"key":"42_CR6","doi-asserted-by":"publisher","first-page":"1204","DOI":"10.1126\/science.aar6170","volume":"360","author":"SA Eslami","year":"2018","unstructured":"Eslami, S.A., et al.: Neural scene representation and rendering. Science 360, 1204\u20131210 (2018)","journal-title":"Science"},{"unstructured":"Rosenbaum, D., Besse, F., Viola, F., Rezende, D.J., Eslami, S.: Learning models for visual 3d localization with implicit mapping. arXiv preprint arXiv:1807.03149 (2018)","key":"42_CR7"},{"unstructured":"Kumar, A., et al.: Consistent generative query networks. arXiv preprint arXiv:1807.02033 (2018)","key":"42_CR8"},{"key":"42_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1007\/978-3-030-20205-7_2","volume-title":"Image Analysis","author":"P Nguyen-Ha","year":"2019","unstructured":"Nguyen-Ha, P., Huynh, L., Rahtu, E., Heikkil\u00e4, J.: Predicting novel views using generative adversarial query network. In: Felsberg, M., Forss\u00e9n, P.-E., Sintorn, I.-M., Unger, J. (eds.) SCIA 2019. LNCS, vol. 11482, pp. 16\u201327. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-20205-7_2"},{"unstructured":"Tobin, J., Zaremba, W., Abbeel, P.: Geometry-aware neural rendering. In: Advances in Neural Information Processing Systems 32. Curran Associates, Inc. (2019)","key":"42_CR10"},{"unstructured":"Vaswani, A., et al.: Attention is all you need. In: Guyon, I., et al. (eds.) Advances in Neural Information Processing Systems 30, pp. 5998\u20136008. Curran Associates, Inc. (2017)","key":"42_CR11"},{"unstructured":"Tewari, A., et al.: State of the art on neural rendering. CoRR abs\/2004.03805 (2020)","key":"42_CR12"},{"doi-asserted-by":"crossref","unstructured":"Olszewski, K., Tulyakov, S., Woodford, O., Li, H., Luo, L.: Transformable bottleneck networks (2019)","key":"42_CR13","DOI":"10.1109\/ICCV.2019.00774"},{"unstructured":"Chen, X., Song, J., Hilliges, O.: Monocular neural image based rendering with continuous view control. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4090\u20134100 (2019)","key":"42_CR14"},{"key":"42_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"322","DOI":"10.1007\/978-3-319-46478-7_20","volume-title":"Computer Vision \u2013 ECCV 2016","author":"M Tatarchenko","year":"2016","unstructured":"Tatarchenko, M., Dosovitskiy, A., Brox, T.: Multi-view 3D models from single images with a convolutional network. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9911, pp. 322\u2013337. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46478-7_20"},{"doi-asserted-by":"crossref","unstructured":"Zhou, T., Tulsiani, S., Sun, W., Malik, J., Efros, A.A.: View synthesis by appearance flow. CoRR abs\/1605.03557 (2016)","key":"42_CR16","DOI":"10.1007\/978-3-319-46493-0_18"},{"key":"42_CR17","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"},{"doi-asserted-by":"crossref","unstructured":"Flynn, J., Neulander, I., Philbin, J., Snavely, N.: Deep stereo: learning to predict new views from the world\u2019s imagery. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5515\u20135524 (2016)","key":"42_CR18","DOI":"10.1109\/CVPR.2016.595"},{"doi-asserted-by":"crossref","unstructured":"Zhou, T., Tucker, R., Flynn, J., Fyffe, G., Snavely, N.: Stereo magnification: learning view synthesis using multiplane images. In: SIGGRAPH (2018)","key":"42_CR19","DOI":"10.1145\/3197517.3201323"},{"key":"42_CR20","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2980179.2980251","volume":"35","author":"NK Kalantari","year":"2016","unstructured":"Kalantari, N.K., Wang, T.C., Ramamoorthi, R.: Learning-based view synthesis for light field cameras. ACM Trans. Graph. 35, 1\u201310 (2016)","journal-title":"ACM Trans. Graph."},{"doi-asserted-by":"crossref","unstructured":"Srinivasan, P.P., Tucker, R., Barron, J.T., Ramamoorthi, R., Ng, R., Snavely, N.: Pushing the boundaries of view extrapolation with multiplane images. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2019, Long Beach, CA, USA, 16\u201320 June 2019, pp. 175\u2013184. Computer Vision Foundation\/IEEE (2019)","key":"42_CR21","DOI":"10.1109\/CVPR.2019.00026"},{"doi-asserted-by":"crossref","unstructured":"Choi, I., Gallo, O., Troccoli, A., Kim, M.H., Kautz, J.: Extreme view synthesis. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 7781\u20137790 (2019)","key":"42_CR22","DOI":"10.1109\/ICCV.2019.00787"},{"doi-asserted-by":"crossref","unstructured":"Tucker, R., Snavely, N.: Single-view view synthesis with multiplane images. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","key":"42_CR23","DOI":"10.1109\/CVPR42600.2020.00063"},{"key":"42_CR24","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3306346.3322980","volume":"38","author":"B Mildenhall","year":"2019","unstructured":"Mildenhall, B., et al.: Local light field fusion: practical view synthesis with prescriptive sampling guidelines. ACM Trans. Graph. 38, 1\u201314 (2019)","journal-title":"ACM Trans. Graph."},{"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: The IEEE International Conference on Computer Vision (ICCV) (2019)","key":"42_CR25","DOI":"10.1109\/ICCV.2019.00768"},{"doi-asserted-by":"crossref","unstructured":"Sitzmann, V., Thies, J., Heide, F., Nie\u00dfner, M., Wetzstein, G., Zollh\u00f6fer, M.: DeepVoxels: learning persistent 3D feature embeddings. In: Proceedings of the Computer Vision and Pattern Recognition (CVPR). IEEE (2019)","key":"42_CR26","DOI":"10.1109\/CVPR.2019.00254"},{"doi-asserted-by":"crossref","unstructured":"Lombardi, S., Simon, T., Saragih, J., Schwartz, G., Lehrmann, A., Sheikh, Y.: Neural volumes: Learning dynamic renderable volumes from images. ACM Trans. Graph. 38 (2019)","key":"42_CR27","DOI":"10.1145\/3306346.3323020"},{"unstructured":"Goodfellow, I., et al.: Generative adversarial nets. In: Ghahramani, Z., Welling, M., Cortes, C., Lawrence, N.D., Weinberger, K.Q. (eds.) Advances in Neural Information Processing Systems 27, pp. 2672\u20132680. Curran Associates, Inc. (2014)","key":"42_CR28"},{"unstructured":"Sitzmann, V., Zollhoefer, M., Wetzstein, G.: Scene representation networks: continuous 3D-structure-aware neural scene representations. In: Advances in Neural Information Processing Systems 32, pp. 1121\u20131132. Curran Associates, Inc. (2019)","key":"42_CR29"},{"unstructured":"Ha, D., Dai, A.M., Le, Q.V.: Hypernetworks. In: 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, 24\u201326 April 2017, Conference Track Proceedings, OpenReview.net (2017)","key":"42_CR30"},{"key":"42_CR31","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"405","DOI":"10.1007\/978-3-030-58452-8_24","volume-title":"Computer Vision \u2013 ECCV 2020","author":"B Mildenhall","year":"2020","unstructured":"Mildenhall, B., Srinivasan, P.P., Tancik, M., Barron, J.T., Ramamoorthi, R., Ng, R.: NeRF: representing scenes as neural radiance fields for view synthesis. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 405\u2013421. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_24"},{"key":"42_CR32","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"178","DOI":"10.1007\/978-3-030-58452-8_11","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Z Li","year":"2020","unstructured":"Li, Z., Xian, W., Davis, A., Snavely, N.: Crowdsampling the plenoptic function. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 178\u2013196. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_11"},{"unstructured":"Dupont, E., et al.: Equivariant neural rendering (2020)","key":"42_CR33"},{"doi-asserted-by":"crossref","unstructured":"Niemeyer, M., Mescheder, L., Oechsle, M., Geiger, A.: Differentiable volumetric rendering: learning implicit 3D representations without 3D supervision (2019)","key":"42_CR34","DOI":"10.1109\/CVPR42600.2020.00356"},{"unstructured":"Garnelo, M., et al.: Conditional neural processes. In: Dy, J., Krause, A. (eds.) Proceedings of the 35th International Conference on Machine Learning. Volume 80 of Proceedings of Machine Learning Research, Stockholmsm\u00e4ssan, Stockholm Sweden, pp. 1704\u20131713 PMLR (2018)","key":"42_CR35"},{"unstructured":"Kim, H., et al.: Attentive neural processes. In: 7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA, 6\u20139 May 2019, OpenReview.net (2019)","key":"42_CR36"},{"unstructured":"Gregor, K., Danihelka, I., Graves, A., Rezende, D., Wierstra, D.: Draw: a recurrent neural network for image generation. In: Bach, F., Blei, D. (eds.) Proceedings of the 32nd International Conference on Machine Learning. Volume 37 of Proceedings of Machine Learning Research, Lille, France, pp. 1462\u20131471. PMLR (2015)","key":"42_CR37"},{"unstructured":"Gregor, K., Besse, F., Jimenez Rezende, D., Danihelka, I., Wierstra, D.: Towards conceptual compression. In: Lee, D.D., Sugiyama, M., Luxburg, U.V., Guyon, I., Garnett, R. (eds.) Advances in Neural Information Processing Systems 29, pp. 3549\u20133557. Curran Associates, Inc. (2016)","key":"42_CR38"},{"unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), Minneapolis, Minnesota, pp. 4171\u20134186. Association for Computational Linguistics (2019)","key":"42_CR39"},{"key":"42_CR40","first-page":"9","volume":"1","author":"A Radford","year":"2019","unstructured":"Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I.: Language models are unsupervised multitask learners. OpenAI Blog 1, 9 (2019)","journal-title":"OpenAI Blog"},{"doi-asserted-by":"crossref","unstructured":"Dai, Z., Yang, Z., Yang, Y., Carbonell, J., Le, Q., Salakhutdinov, R.: Transformer-XL: attentive language models beyond a fixed-length context. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, Florence, Italy, pp. 2978\u20132988. Association for Computational Linguistics (2019)","key":"42_CR41","DOI":"10.18653\/v1\/P19-1285"},{"key":"42_CR42","doi-asserted-by":"publisher","first-page":"307","DOI":"10.1561\/2200000056","volume":"12","author":"DP Kingma","year":"2019","unstructured":"Kingma, D.P., Welling, M.: An introduction to variational autoencoders. Found. Trends Mach. Learn. 12, 307\u2013392 (2019)","journal-title":"Found. Trends Mach. Learn."},{"unstructured":"Higgins, I., et al.: beta-VAE: learning basic visual concepts with a constrained variational framework. In: ICLR (2017)","key":"42_CR43"},{"unstructured":"Chang, A.X., et al.: ShapeNet: an information-rich 3D model repository (2015)","key":"42_CR44"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2020"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-69538-5_42","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,18]],"date-time":"2022-12-18T22:03:42Z","timestamp":1671401022000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-69538-5_42"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030695378","9783030695385"],"references-count":44,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-69538-5_42","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"25 February 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kyoto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","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":"30 November 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 December 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"accv2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/accv2020.kyoto\/","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":"768","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":"254","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":"33% - 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":"3","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.","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)"}}]}}