{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T05:08:49Z","timestamp":1780463329301,"version":"3.54.1"},"reference-count":55,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2023,5,10]],"date-time":"2023-05-10T00:00:00Z","timestamp":1683676800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,5,10]],"date-time":"2023-05-10T00:00:00Z","timestamp":1683676800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61972162"],"award-info":[{"award-number":["61972162"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Guangdong International Science and Technology Cooperation Project","award":["2021A0505030009"],"award-info":[{"award-number":["2021A0505030009"]}]},{"DOI":"10.13039\/501100003453","name":"Natural Science Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2021A1515012625"],"award-info":[{"award-number":["2021A1515012625"]}],"id":[{"id":"10.13039\/501100003453","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Guangzhou Basic and Applied Research Project","award":["202102021074"],"award-info":[{"award-number":["202102021074"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2023,8]]},"DOI":"10.1007\/s11263-023-01803-z","type":"journal-article","created":{"date-parts":[[2023,5,11]],"date-time":"2023-05-11T09:35:17Z","timestamp":1683797717000},"page":"2032-2043","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Single-View View Synthesis with Self-rectified Pseudo-Stereo"],"prefix":"10.1007","volume":"131","author":[{"given":"Yang","family":"Zhou","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hanjie","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenxi","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zheng","family":"Xiong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Qin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3802-4644","authenticated-orcid":false,"given":"Shengfeng","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,5,10]]},"reference":[{"key":"1803_CR1","doi-asserted-by":"crossref","unstructured":"Aliev, K. A., Ulyanov, D., & Lempitsky, V. S. (2020). Neural point-based graphics. In ECCV","DOI":"10.1007\/978-3-030-58542-6_42"},{"key":"1803_CR2","doi-asserted-by":"publisher","first-page":"30:1","DOI":"10.1145\/2487228.2487238","volume":"32","author":"G Chaurasia","year":"2013","unstructured":"Chaurasia, G., Duch\u00eane, S., Sorkine-Hornung, O., & Drettakis, G. (2013). Depth synthesis and local warps for plausible image-based navigation. ACM TOG, 32, 30:1-30:12.","journal-title":"ACM TOG"},{"key":"1803_CR3","unstructured":"Chen, X., Duan, Y., Houthooft, R., Schulman, J., Sutskever, I., & Abbeel, P. (2016). Infogan: Interpretable representation learning by information maximizing generative adversarial nets. In NeurIPS"},{"key":"1803_CR4","doi-asserted-by":"crossref","unstructured":"Choi, I., Gallo, O., Troccoli, A. J., Kim, M. H., & Kautz, J. (2019). Extreme view synthesis. In ICCV (pp. 7780\u20137789).","DOI":"10.1109\/ICCV.2019.00787"},{"key":"1803_CR5","doi-asserted-by":"publisher","first-page":"52","DOI":"10.1109\/MCG.2018.2884188","volume":"39","author":"X Cun","year":"2019","unstructured":"Cun, X., Xu, F., Pun, C. M., & Gao, H. (2019). Depth-assisted full resolution network for single image-based view synthesis. IEEE Computer Graphics and Applications, 39, 52\u201364.","journal-title":"IEEE Computer Graphics and Applications"},{"key":"1803_CR6","doi-asserted-by":"crossref","unstructured":"Debevec, P. E., Taylor, C. J., & Malik, J. (1996). Modeling and rendering architecture from photographs: A hybrid geometry-and image-based approach. In Proceedings of the 23rd annual conference on Computer graphics and interactive techniques (pp. 11\u201320).","DOI":"10.1145\/237170.237191"},{"key":"1803_CR7","doi-asserted-by":"crossref","unstructured":"Debevec, P. E., Yu, Y., & Borshukov, G. (1998). Efficient view-dependent image-based rendering with projective texture-mapping. In Rendering Techniques.","DOI":"10.1007\/978-3-7091-6453-2_10"},{"key":"1803_CR8","doi-asserted-by":"publisher","first-page":"141","DOI":"10.1007\/s11263-005-6643-9","volume":"63","author":"AW Fitzgibbon","year":"2005","unstructured":"Fitzgibbon, A. W., Wexler, Y., & Zisserman, A. (2005). Image-based rendering using image-based priors. International Journal of Computer Vision, 63, 141\u2013151.","journal-title":"International Journal of Computer Vision"},{"key":"1803_CR9","doi-asserted-by":"crossref","unstructured":"Flynn, J., Broxton, M., Debevec, P. E., DuVall, M., Fyffe, G., Overbeck, R. S., Snavely, N., & Tucker, R. (2019) Deepview: View synthesis with learned gradient descent. In CVPR (pp. 2362\u20132371).","DOI":"10.1109\/CVPR.2019.00247"},{"key":"1803_CR10","unstructured":"Frankle, J., Dziugaite, G. K., Roy, D. M., & Carbin, M. (2019). The lottery ticket hypothesis at scale. arXiv:1903.01611"},{"key":"1803_CR11","doi-asserted-by":"publisher","first-page":"1231","DOI":"10.1177\/0278364913491297","volume":"32","author":"A Geiger","year":"2013","unstructured":"Geiger, A., Lenz, P., Stiller, C., & Urtasun, R. (2013). Vision meets robotics: The kitti dataset. The International Journal of Robotics Research, 32, 1231\u20131237.","journal-title":"The International Journal of Robotics Research"},{"key":"1803_CR12","doi-asserted-by":"crossref","unstructured":"Godard, C., Aodha, O. M., & Brostow, G. J. (2017). Unsupervised monocular depth estimation with left-right consistency. In CVPR (pp. 6602\u20136611).","DOI":"10.1109\/CVPR.2017.699"},{"key":"1803_CR13","unstructured":"GonzalezBello, J. L., & Kim, M. (2020). Forget about the lidar: Self-supervised depth estimators with med probability volumes. In NeurIPS"},{"key":"1803_CR14","unstructured":"Gonzalez, J. L., & Kim, M. (2021). Plade-net: Towards pixel-level accuracy for self-supervised single-view depth estimation with neural positional encoding and distilled matting loss. In CVPR."},{"key":"1803_CR15","first-page":"1","volume":"37","author":"P Hedman","year":"2018","unstructured":"Hedman, P., Philip, J., Price, T., Frahm, J. M., Drettakis, G., & Brostow, G. J. (2018). Deep blending for free-viewpoint image-based rendering. ACM TOG, 37, 1\u201315.","journal-title":"ACM TOG"},{"key":"1803_CR16","unstructured":"Hooker, S., Courville, A., Clark, G., Dauphin, Y., & Frome, A. (2019). What do compressed deep neural networks forget? arXiv"},{"key":"1803_CR17","doi-asserted-by":"crossref","unstructured":"Ilg, E., Mayer, N., Saikia, T., Keuper, M., Dosovitskiy, A., & Brox, T. (2017). Flownet 2.0: Evolution of optical flow estimation with deep networks. In CVPR (pp. 2462\u20132470).","DOI":"10.1109\/CVPR.2017.179"},{"key":"1803_CR18","doi-asserted-by":"crossref","unstructured":"Jampani, V., Chang, H., Sargent, K., Kar, A., Tucker, R., Krainin, M., Kaeser, D., Freeman, W. T., Salesin, D., Curless, B., et\u00a0al. (2021). Slide: Single image 3d photography with soft layering and depth-aware inpainting. In ICCV (pp. 12518\u201312527).","DOI":"10.1109\/ICCV48922.2021.01229"},{"key":"1803_CR19","doi-asserted-by":"crossref","unstructured":"Jantet, V., Morin, L., & Guillemot, C. (2009). Incremental-ldi for multi-view coding. In 3DTV (pp. 1\u20134).","DOI":"10.1109\/3DTV.2009.5069647"},{"key":"1803_CR20","unstructured":"Jiang, Z., Chen, T., Mortazavi, B. J., & Wang, Z. (2021). Self-damaging contrastive learning. arXiv:2106.02990"},{"key":"1803_CR21","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., & Aila, T. (2019). A style-based generator architecture for generative adversarial networks. In CVPR (pp. 4396\u20134405).","DOI":"10.1109\/CVPR.2019.00453"},{"key":"1803_CR22","unstructured":"Kingma, D. P., Ba, J. (2015). Adam: A method for stochastic optimization. In ICLR"},{"key":"1803_CR23","first-page":"1","volume":"32","author":"J Kopf","year":"2013","unstructured":"Kopf, J., Langguth, F., Scharstein, D., Szeliski, R., & Goesele, M. (2013). Image-based rendering in the gradient domain. ACM TOG, 32, 1\u20139.","journal-title":"ACM TOG"},{"issue":"4","key":"1803_CR24","doi-asserted-by":"publisher","first-page":"76:1","DOI":"10.1145\/3386569.3392420","volume":"39","author":"J Kopf","year":"2020","unstructured":"Kopf, J., Matzen, K., Alsisan, S., Quigley, O., Ge, F., Chong, Y., Patterson, J., Frahm, J. M., Wu, S., Yu, M., et al. (2020). One shot 3d photography. ACM TOG, 39(4), 76:1-76:13.","journal-title":"ACM TOG"},{"key":"1803_CR25","unstructured":"Kulkarni, T. D., Whitney, W. F., Kohli, P., & Tenenbaum, J. B. (2015). Deep convolutional inverse graphics network. In NeurIPS."},{"key":"1803_CR26","unstructured":"Li, H., Kadav, A., Durdanovic, I., Samet, H., & Graf, H. P. (2017). Pruning filters for efficient convnets. arXiv:1608.08710"},{"key":"1803_CR27","doi-asserted-by":"crossref","unstructured":"Li, J., Feng, Z., She, Q., Ding, H., Wang, C., & Lee, G. H. (2021). Mine: Towards continuous depth mpi with nerf for novel view synthesis. In ICCV (pp. 12578\u201312588).","DOI":"10.1109\/ICCV48922.2021.01235"},{"key":"1803_CR28","doi-asserted-by":"crossref","unstructured":"Liu, Z., Li, J., Shen, Z., Huang, G., Yan, S., & Zhang, C. (2017). Learning efficient convolutional networks through network slimming. In ICCV (pp. 2755\u20132763).","DOI":"10.1109\/ICCV.2017.298"},{"key":"1803_CR29","doi-asserted-by":"crossref","unstructured":"Luo, Y., Ren, J., Lin, M., Pang, J., Sun, W., Li, H., & Lin, L. (2018). Single view stereo matching. In CVPR (pp. 155\u2013163).","DOI":"10.1109\/CVPR.2018.00024"},{"key":"1803_CR30","doi-asserted-by":"crossref","unstructured":"Martin-Brualla, R., Pandey, R., Yang, S., Pidlypenskyi, P., Taylor, J., Valentin, J. P. C., Khamis, S., Davidson, P. L., Tkach, A., Lincoln, P., Kowdle, A., Rhemann, C., Goldman, D. B., Keskin, C., Seitz, S. M., Izadi, S., & Fanello, S. (2018). Lookingood: Enhancing performance capture with real-time neural re-rendering. ACM TOG 37, 255:1\u2013255:14.","DOI":"10.1145\/3272127.3275099"},{"key":"1803_CR31","doi-asserted-by":"crossref","unstructured":"Mayer, N., Ilg, E., Hausser, P., Fischer, P., Cremers, D., Dosovitskiy, A., & Brox, T. (2016). A large dataset to train convolutional networks for disparity, optical flow, and scene flow estimation. In CVPR (pp. 4040\u20134048).","DOI":"10.1109\/CVPR.2016.438"},{"key":"1803_CR32","doi-asserted-by":"crossref","unstructured":"Meshry, M., Goldman, D. B., Khamis, S., Hoppe, H., Pandey, R., Snavely, N., & Martin-Brualla, R. (2019). Neural rerendering in the wild. In CVPR (pp. 6871\u20136880).","DOI":"10.1109\/CVPR.2019.00704"},{"key":"1803_CR33","doi-asserted-by":"crossref","unstructured":"Mildenhall, B., Srinivasan, P. P., Tancik, M., Barron, J. T., Ramamoorthi, R., & Ng, R. (2020). Nerf: Representing scenes as neural radiance fields for view synthesis. In ECCV.","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"1803_CR34","unstructured":"Novotn\u00fd, D., Graham, B., & Reizenstein, J. (2019). Perspectivenet: A scene-consistent image generator for new view synthesis in real indoor environments. In NeurIPS."},{"key":"1803_CR35","doi-asserted-by":"crossref","unstructured":"Park, E., Yang, J., Yumer, E., Ceylan, D., & Berg, A. C. (2017). Transformation-grounded image generation network for novel 3d view synthesis. In CVPR (pp. 702\u2013711).","DOI":"10.1109\/CVPR.2017.82"},{"key":"1803_CR36","doi-asserted-by":"crossref","unstructured":"Park, K., Sinha, U., Barron, J. T., Bouaziz, S., Goldman, D. B., Seitz, S. M., & Brualla, R. M. (2020). Deformable neural radiance fields. arXiv:2011.12948","DOI":"10.1109\/ICCV48922.2021.00581"},{"key":"1803_CR37","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3130800.3130855","volume":"36","author":"E Penner","year":"2017","unstructured":"Penner, E., & Zhang, L. (2017). Soft 3d reconstruction for view synthesis. ACM TOG, 36, 1\u201311.","journal-title":"ACM TOG"},{"key":"1803_CR38","doi-asserted-by":"crossref","unstructured":"Seitz, S. M., Curless, B., Diebel, J., Scharstein, D., & Szeliski, R. (2006). A comparison and evaluation of multi-view stereo reconstruction algorithms. In CVPR (pp. 519\u2013528).","DOI":"10.1109\/CVPR.2006.19"},{"key":"1803_CR39","doi-asserted-by":"crossref","unstructured":"Shih, M. L., Su, S. Y., Kopf, J., & Huang, J. B. (2020). 3d photography using context-aware layered depth inpainting. In CVPR (pp. 8025\u20138035).","DOI":"10.1109\/CVPR42600.2020.00805"},{"key":"1803_CR40","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2185520.2185596","volume":"31","author":"SN Sinha","year":"2012","unstructured":"Sinha, S. N., Kopf, J., Goesele, M., Scharstein, D., & Szeliski, R. (2012). Image-based rendering for scenes with reflections. ACM TOG, 31, 1\u201310.","journal-title":"ACM TOG"},{"key":"1803_CR41","doi-asserted-by":"crossref","unstructured":"Srinivasan, P. P., Tucker, R., Barron, J. T., Ramamoorthi, R., Ng, R., & Snavely, N. (2019). Pushing the boundaries of view extrapolation with multiplane images. In CVPR (pp. 175\u2013184).","DOI":"10.1109\/CVPR.2019.00026"},{"key":"1803_CR42","doi-asserted-by":"crossref","unstructured":"Srinivasan, P. P., Wang, T., Sreelal, A., Ramamoorthi, R., & Ng, R. (2017). Learning to synthesize a 4d rgbd light field from a single image. In ICCV.","DOI":"10.1109\/ICCV.2017.246"},{"key":"1803_CR43","doi-asserted-by":"crossref","unstructured":"Sun, S. H., Huh, M., Liao, Y. H., Zhang, N., Lim, J. J. (2018). Multi-view to novel view: Synthesizing novel views with self-learned confidence. In ECCV.","DOI":"10.1007\/978-3-030-01219-9_10"},{"key":"1803_CR44","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1023\/A:1008192912624","volume":"32","author":"R Szeliski","year":"2004","unstructured":"Szeliski, R., & Golland, P. (2004). Stereo matching with transparency and matting. International Journal of Computer Vision, 32, 45\u201361.","journal-title":"International Journal of Computer Vision"},{"key":"1803_CR45","doi-asserted-by":"crossref","unstructured":"Tatarchenko, M., Dosovitskiy, A., & Brox, T. (2016). Multi-view 3d models from single images with a convolutional network. In ECCV.","DOI":"10.1007\/978-3-319-46478-7_20"},{"key":"1803_CR46","doi-asserted-by":"crossref","unstructured":"Tucker, R., & Snavely, N. (2020). Single-view view synthesis with multiplane images. In CVPR (pp. 548\u2013557).","DOI":"10.1109\/CVPR42600.2020.00063"},{"key":"1803_CR47","doi-asserted-by":"crossref","unstructured":"Tulsiani, S., Tucker, R., & Snavely, N. (2018). Layer-structured 3d scene inference via view synthesis. In ECCV.","DOI":"10.1007\/978-3-030-01234-2_19"},{"key":"1803_CR48","doi-asserted-by":"crossref","unstructured":"Wang, Z., Wang, H., Chen, T., Wang, Z., & Ma, K. (2021). Troubleshooting blind image quality models in the wild. In CVPR (pp. 16251\u201316260).","DOI":"10.1109\/CVPR46437.2021.01599"},{"key":"1803_CR49","doi-asserted-by":"crossref","unstructured":"Watson, J., Mac\u00a0A. O., Turmukhambetov, D., Brostow, G. J., & Firman, M. (2020). Learning stereo from single images. In ECCV (pp. 722\u2013740).","DOI":"10.1007\/978-3-030-58452-8_42"},{"key":"1803_CR50","doi-asserted-by":"crossref","unstructured":"Xie, J., Girshick, R. B., Farhadi, A. (2016). Deep3d: Fully automatic 2d-to-3d video conversion with deep convolutional neural networks. In ECCV.","DOI":"10.1007\/978-3-319-46493-0_51"},{"key":"1803_CR51","unstructured":"Yu, F., & Koltun, V. (2016). Multi-scale context aggregation by dilated convolutions. CoRR arXiv:1511.07122"},{"key":"1803_CR52","doi-asserted-by":"crossref","unstructured":"Yu, J., Lin, Z., Yang, J., Shen, X., Lu, X., Huang, T. S. (2019). Free-form image inpainting with gated convolution. In ICCV (pp. 4471\u20134480).","DOI":"10.1109\/ICCV.2019.00457"},{"key":"1803_CR53","doi-asserted-by":"crossref","unstructured":"Zhang, R., Isola, P., Efros, A. A., Shechtman, E., & Wang, O. (2018). The unreasonable effectiveness of deep features as a perceptual metric. In CVPR (pp. 586\u2013595).","DOI":"10.1109\/CVPR.2018.00068"},{"issue":"4","key":"1803_CR54","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3197517.3201292","volume":"37","author":"T Zhou","year":"2018","unstructured":"Zhou, T., Tucker, R., Flynn, J., Fyffe, G., & Snavely, N. (2018). Stereo magnification: Learning view synthesis using multiplane images. ACM TOG, 37(4), 1\u201312.","journal-title":"ACM TOG"},{"key":"1803_CR55","doi-asserted-by":"crossref","unstructured":"Zhou, T., Tulsiani, S., Sun, W., Malik, J., Efros, A. A. (2016). View synthesis by appearance flow. arXiv:1605.03557","DOI":"10.1007\/978-3-319-46493-0_18"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-023-01803-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-023-01803-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-023-01803-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,17]],"date-time":"2023-07-17T07:10:33Z","timestamp":1689577833000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-023-01803-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,10]]},"references-count":55,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2023,8]]}},"alternative-id":["1803"],"URL":"https:\/\/doi.org\/10.1007\/s11263-023-01803-z","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,5,10]]},"assertion":[{"value":"21 September 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 April 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 May 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}