{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T17:57:16Z","timestamp":1768240636827,"version":"3.49.0"},"reference-count":45,"publisher":"Association for Computing Machinery (ACM)","issue":"1","funder":[{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"crossref","award":["62325206, 62401285 and 61936005"],"award-info":[{"award-number":["62325206, 62401285 and 61936005"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Key Research and Development Program of Jiangsu Province","award":["BE2023016-4"],"award-info":[{"award-number":["BE2023016-4"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Multimedia Comput. Commun. Appl."],"published-print":{"date-parts":[[2026,1,31]]},"abstract":"<jats:p>Light field reconstruction is one of the most important techniques for future glass-free 3D media production. However, current techniques suffer from low view-consistency and fixed patterns of view-trajectory. This article presents the 3D Multi-orientation Epipolar Plane Image (MOEPI) representation for high-quality light field reconstruction with both the inter-view and extra-view settings. Each layer in MOEPI is composed of EPI lines with a fixed orientation. To infer the MOEPI, a new Multi-reference Focal Stack (MRFS) intermediate representation is proposed. The optimization of MOEPI could be regarded as the problem of the most-focused content extraction from the MRFS. This optimization is implemented with a 3D U-shaped network. We also propose the LPIPS-EPI metric for evaluating the view-consistency. Experiments on light fields with both high and low signal-to-noise ratios demonstrate that the proposed MOEPI representation could synthesize high-quality light fields especially in occlusion or un-captured areas.<\/jats:p>","DOI":"10.1145\/3777898","type":"journal-article","created":{"date-parts":[[2025,11,21]],"date-time":"2025-11-21T14:46:42Z","timestamp":1763736402000},"page":"1-22","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Light Field Reconstruction Using Multi-orientation Epipolar Plane Images"],"prefix":"10.1145","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5233-4959","authenticated-orcid":false,"given":"Yaning","family":"Li","sequence":"first","affiliation":[{"name":"The School of Artificial Intelligence, Nanjing University of Posts and Telecommunications, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6756-9571","authenticated-orcid":false,"given":"Hao","family":"Zhu","sequence":"additional","affiliation":[{"name":"The School of Electronic Science and Engineering, Nanjing University, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5956-831X","authenticated-orcid":false,"given":"Bing-Kun","family":"Bao","sequence":"additional","affiliation":[{"name":"The School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing, China"}]}],"member":"320","published-online":{"date-parts":[[2026,1,12]]},"reference":[{"key":"e_1_3_2_2_2","unstructured":"[n.\u2009d.]. The New Stanford Light Field Archive. Retrieved from http:\/\/lightfield.stanford.edu\/lfs.html"},{"key":"e_1_3_2_3_2","first-page":"19819","volume-title":"IEEE CVPR","author":"Attal Benjamin","year":"2022","unstructured":"Benjamin Attal, Jia-Bin Huang, Michael Zollh\u00f6fer, Johannes Kopf, and Changil Kim. 2022. Learning neural light fields with ray-space embedding. In IEEE CVPR, 19819\u201319829."},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1145\/344779.344932"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1145\/3366371"},{"key":"e_1_3_2_6_2","first-page":"15191","volume-title":"IEEE CVPR","author":"Chen Tianlong","year":"2022","unstructured":"Tianlong Chen, Peihao Wang, Zhiwen Fan, and Zhangyang Wang. 2022. Aug-nerf: Training stronger neural radiance fields with triple-level physically-grounded augmentations. In IEEE CVPR, 15191\u201315202."},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2439281"},{"key":"e_1_3_2_8_2","first-page":"5515","volume-title":"IEEE CVPR","author":"Flynn John","year":"2016","unstructured":"John Flynn, Ivan Neulander, James Philbin, and Noah Snavely. 2016. Deepstereo: Learning to predict new views from the world\u2019s imagery. In IEEE CVPR, 5515\u20135524."},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/3459098"},{"key":"e_1_3_2_10_2","first-page":"8999","article-title":"Spatial-angular attention network for light field reconstruction","author":"Gaochang Wu","year":"2021","unstructured":"Wu Gaochang, Wang Yingqian, Liu Yebin, Fang Lu, and Chai Tianyou. 2021. Spatial-angular attention network for light field reconstruction. IEEE Trans. Image Process. 30 (2021), 8999\u20139013.","journal-title":"IEEE Trans. Image Process."},{"key":"e_1_3_2_11_2","first-page":"263","article-title":"Spatio-angular resolution tradeoffs in integral photography","author":"Georgiev Todor","year":"2006","unstructured":"Todor Georgiev, Ke Colin Zheng, Brian Curless, David Salesin, Shree K. Nayar, and Chintan Intwala. 2006. Spatio-angular resolution tradeoffs in integral photography. In Rendering Techniques, 263\u2013272.","journal-title":"Rendering Techniques"},{"key":"e_1_3_2_12_2","first-page":"1","volume-title":"Springer ACCV","author":"Guo Mantang","year":"2018","unstructured":"Mantang Guo, Hao Zhu, Guoqing Zhou, and Qing Wang. 2018. Dense light field reconstruction from sparse sampling using residual network. In Springer ACCV, 1\u201314."},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1145\/3272127.3275084"},{"key":"e_1_3_2_14_2","first-page":"19","volume-title":"Springer ACCV","author":"Honauer Katrin","year":"2016","unstructured":"Katrin Honauer, Ole Johannsen, Daniel Kondermann, and Bastian Goldluecke. 2016. A dataset and evaluation methodology for depth estimation on 4d light fields. In Springer ACCV, 19\u201334."},{"key":"e_1_3_2_15_2","unstructured":"Andrew G. Howard Menglong Zhu Bo Chen Dmitry Kalenichenko Weijun Wang Tobias Weyand Marco Andreetto and Hartwig Adam. 2017. Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv:1704.04861. Retrieved from https:\/\/arxiv.org\/abs\/1704.04861"},{"key":"e_1_3_2_16_2","first-page":"46","volume-title":"IEEE CVPR","author":"Jiang Yifan","year":"2023","unstructured":"Yifan Jiang, Peter Hedman, Ben Mildenhall, Dejia Xu, Jonathan T. Barron, Zhangyang Wang, and Tianfan Xue. 2023. AligNeRF: High-fidelity neural radiance fields via alignment-aware training. In IEEE CVPR, 46\u201355."},{"issue":"6","key":"e_1_3_2_17_2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/2980179.2980251","article-title":"Learning-based view synthesis for light field cameras","volume":"35","author":"Khademi Kalantari Nima","year":"2016","unstructured":"Nima Khademi Kalantari, Ting-Chun Wang, and Ravi Ramamoorthi. 2016. Learning-based view synthesis for light field cameras. ACM Trans. Graph. 35, 6 (2016), 1\u201310.","journal-title":"ACM Trans. Graph"},{"issue":"4","key":"e_1_3_2_18_2","first-page":"76","article-title":"One shot 3D photography","volume":"39","author":"Kopf Johannes","year":"2020","unstructured":"Johannes Kopf, Kevin Matzen, Suhib Alsisan, Ocean Quigley, Francis Ge, Yangming Chong, Josh Patterson, Jan-Michael Frahm, Shu Wu, Matthew Yu, et al. 2020. One shot 3D photography. ACM Trans. Graph. 39, 4 (2020), 76\u201371.","journal-title":"ACM Trans. Graph"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2922099"},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/237170.237199"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3337516"},{"key":"e_1_3_2_22_2","first-page":"1328","article-title":"Deep anti-aliasing of whole focal stack using slice spectrum","author":"Li Yaning","year":"2021","unstructured":"Yaning Li, Xue Wang, Hao Zhu, Zhou Guoqing, and Qing Wang. 2021. Deep anti-aliasing of whole focal stack using slice spectrum. IEEE Trans. Comput. Imaging. 7 (2021), 1328\u20131340.","journal-title":"IEEE Trans. Comput. Imaging"},{"key":"e_1_3_2_23_2","first-page":"109551","article-title":"Dense light field reconstruction based on epipolar focus spectrum","author":"Li Yaning","year":"2023","unstructured":"Yaning Li, Xue Wang, Hao Zhu, Guoqing Zhou, and Qing Wang. 2023. Dense light field reconstruction based on epipolar focus spectrum. Pattern Recognit. 140 (2023), 109551.","journal-title":"Pattern Recognit"},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2945027"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3322980"},{"key":"e_1_3_2_26_2","first-page":"405","volume-title":"Springer ECCV","author":"Mildenhall Ben","year":"2020","unstructured":"Ben Mildenhall, Pratul P. Srinivasan, Matthew Tancik, Jonathan T. Barron, Ravi Ramamoorthi, and Ren Ng. 2020. Nerf: Representing scenes as neural radiance fields for view synthesis. In Springer ECCV, 405\u2013421."},{"key":"e_1_3_2_27_2","unstructured":"S. Moreschini F. Gama R. Bregovic and A. Gotchev. [n.\u2009d.]. CIVIT Dataset: Horizontal-Parallax-Only Densely-Sampled Light-Fields. Retrieved from https:\/\/civit.fi\/densely-sampled-light-field-datasets\/"},{"key":"e_1_3_2_28_2","volume-title":"Digital Light Field Photography","author":"Ng Ren","year":"2006","unstructured":"Ren Ng. 2006. Digital Light Field Photography. Stanford University, CA."},{"key":"e_1_3_2_29_2","first-page":"1","article-title":"Light field photography with a hand-held plenoptic camera","volume":"2","author":"Ng Ren","year":"2005","unstructured":"Ren Ng, Marc Levoy, Mathieu Br\u00e9dif, Gene Duval, Mark Horowitz, and Pat Hanrahan. 2005. Light field photography with a hand-held plenoptic camera. Computer Science Technical Report CSTR 2 (Nov. 2005), 1\u201311.","journal-title":"Computer Science Technical Report CSTR"},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1145\/3130800.3130855"},{"key":"e_1_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2923323"},{"key":"e_1_3_2_32_2","first-page":"8269","volume-title":"IEEE CVPR","author":"Suhail Mohammed","year":"2022","unstructured":"Mohammed Suhail, Carlos Esteves, Leonid Sigal, and Ameesh Makadia. 2022. Light field neural rendering. In IEEE CVPR, 8269\u20138279."},{"issue":"4","key":"e_1_3_2_33_2","first-page":"133","article-title":"Light field video capture using a learning-based hybrid imaging system","volume":"36","author":"Wang Ting-Chun","year":"2017","unstructured":"Ting-Chun Wang, Jun-Yan Zhu, Nima Khademi Kalantari, Alexei A. Efros, and Ravi Ramamoorthi. 2017. Light field video capture using a learning-based hybrid imaging system. ACM Trans. Graph. 36, 4 (2017), 133.","journal-title":"ACM Trans. Graph"},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.147"},{"key":"e_1_3_2_35_2","first-page":"225","volume-title":"VMV","author":"Wanner Sven","year":"2013","unstructured":"Sven Wanner, Stephan Meister, and Bastian Goldluecke. 2013. Datasets and benchmarks for densely sampled 4D light fields. In VMV. Citeseer, 225\u2013226."},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1145\/1073204.1073259"},{"key":"e_1_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2895463"},{"key":"e_1_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2845393"},{"key":"e_1_3_2_39_2","first-page":"6143","volume-title":"IEEE CVPR","author":"Xie Shaowen","year":"2023","unstructured":"Shaowen Xie, Hao Zhu, Zhen Liu, Qi Zhang, You Zhou, Xun Cao, and Zhan Ma. 2023. DINER: Disorder-Invariant implicit neural representation. In IEEE CVPR, 6143\u20136152."},{"key":"e_1_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1145\/3106156"},{"key":"e_1_3_2_41_2","first-page":"586","volume-title":"IEEE CVPR","author":"Zhang Richard","year":"2018","unstructured":"Richard Zhang, Phillip Isola, Alexei A. Efros, Eli Shechtman, and Oliver Wang. 2018. The unreasonable effectiveness of deep features as a perceptual metric. In IEEE CVPR, 586\u2013595."},{"key":"e_1_3_2_42_2","first-page":"8274","volume-title":"IEEE CVPR","author":"Zhang Xiaoshuai","year":"2023","unstructured":"Xiaoshuai Zhang, Abhijit Kundu, Thomas Funkhouser, Leonidas Guibas, Hao Su, and Kyle Genova. 2023. Nerflets: Local radiance fields for efficient structure-aware 3D scene representation from 2D supervision. In IEEE CVPR, 8274\u20138284."},{"key":"e_1_3_2_43_2","first-page":"6848","volume-title":"IEEE CVPR","author":"Zhang Xiangyu","year":"2018","unstructured":"Xiangyu Zhang, Xinyu Zhou, Mengxiao Lin, and Jian Sun. 2018. Shufflenet: An extremely efficient convolutional neural network for mobile devices. In IEEE CVPR, 6848\u20136856."},{"key":"e_1_3_2_44_2","first-page":"12363","volume-title":"IEEE CVPR","author":"Zhou Kun","year":"2023","unstructured":"Kun Zhou, Wenbo Li, Yi Wang, Tao Hu, Nianjuan Jiang, Xiaoguang Han, and Jiangbo Lu. 2023. NeRFLiX: High-quality neural view synthesis by learning a degradation-driven inter-viewpoint MiXer. In IEEE CVPR, 12363\u201312374."},{"key":"e_1_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201292"},{"key":"e_1_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2019.2957761"}],"container-title":["ACM Transactions on Multimedia Computing, Communications, and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3777898","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T14:32:11Z","timestamp":1768228331000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3777898"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,12]]},"references-count":45,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1,31]]}},"alternative-id":["10.1145\/3777898"],"URL":"https:\/\/doi.org\/10.1145\/3777898","relation":{},"ISSN":["1551-6857","1551-6865"],"issn-type":[{"value":"1551-6857","type":"print"},{"value":"1551-6865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,12]]},"assertion":[{"value":"2024-07-02","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-11-15","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-01-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}