{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T10:17:07Z","timestamp":1775470627580,"version":"3.50.1"},"reference-count":79,"publisher":"Association for Computing Machinery (ACM)","issue":"4","license":[{"start":{"date-parts":[[2021,11,12]],"date-time":"2021-11-12T00:00:00Z","timestamp":1636675200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Ministry of Science and Technology of China - Science and Technology Innovations 2030","award":["2019AAA0103501"],"award-info":[{"award-number":["2019AAA0103501"]}]},{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61801303 and 62031013"],"award-info":[{"award-number":["61801303 and 62031013"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100021171","name":"Guangdong Basic and Applied Basic Research Foundation","doi-asserted-by":"crossref","award":["2019A1515012031"],"award-info":[{"award-number":["2019A1515012031"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Shenzhen Science and Technology Plan Basic Research Project","award":["JCYJ20190808161805519"],"award-info":[{"award-number":["JCYJ20190808161805519"]}]},{"name":"Open Projects Program of National Laboratory of Pattern Recognition","award":["202000045"],"award-info":[{"award-number":["202000045"]}]},{"name":"CCF-Tencent Open Fund","award":["RAGR20200114"],"award-info":[{"award-number":["RAGR20200114"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Multimedia Comput. Commun. Appl."],"published-print":{"date-parts":[[2021,11,30]]},"abstract":"<jats:p>View synthesis (VS) for light field images is a very time-consuming task due to the great quantity of involved pixels and intensive computations, which may prevent it from the practical three-dimensional real-time systems. In this article, we propose an acceleration approach for deep learning-based light field view synthesis, which can significantly reduce calculations by using compact-resolution (CR) representation and super-resolution (SR) techniques, as well as light-weight neural networks. The proposed architecture has three cascaded neural networks, including a CR network to generate the compact representation for original input views, a VS network to synthesize new views from down-scaled compact views, and a SR network to reconstruct high-quality views with full resolution. All these networks are jointly trained with the integrated losses of CR, VS, and SR networks. Moreover, due to the redundancy of deep neural networks, we use the efficient light-weight strategy to prune filters for simplification and inference acceleration. Experimental results demonstrate that the proposed method can greatly reduce the processing time and become much more computationally efficient with competitive image quality.<\/jats:p>","DOI":"10.1145\/3459098","type":"journal-article","created":{"date-parts":[[2021,11,12]],"date-time":"2021-11-12T21:16:06Z","timestamp":1636751766000},"page":"1-20","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":30,"title":["A Fast View Synthesis Implementation Method for Light Field Applications"],"prefix":"10.1145","volume":"17","author":[{"given":"Wei","family":"Gao","sequence":"first","affiliation":[{"name":"School of Electronic and Computer Engineering, Shenzhen Graduate School, Peking University, and Artificial Intelligence Research Center, Peng Cheng Laboratory, Nanshan, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Linjie","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Electronic and Computer Engineering, Shenzhen Graduate School, Peking University, and Artificial Intelligence Research Center, Peng Cheng Laboratory, Nanshan, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lvfang","family":"Tao","sequence":"additional","affiliation":[{"name":"School of Electronic and Computer Engineering, Shenzhen Graduate School, Peking University, and Artificial Intelligence Research Center, Peng Cheng Laboratory, Nanshan, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2021,11,12]]},"reference":[{"key":"e_1_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1145\/1276377.1276390"},{"key":"e_1_3_1_3_2","unstructured":"Johannes Ball\u00e9 David Minnen Saurabh Singh Sung Jin Hwang and Nick Johnston. 2018. Variational image compression with a scale hyperprior. In International Conference on Learning Representations . https:\/\/openreview.net\/forum?id=rkcQFMZRb."},{"key":"e_1_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.5555\/2986459.2986743"},{"key":"e_1_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1145\/1150402.1150464"},{"key":"e_1_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1145\/2487228.2487238"},{"key":"e_1_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2706685"},{"key":"e_1_3_1_8_2","article-title":"A survey of model compression and acceleration for deep neural networks","author":"Cheng Yu","year":"2017","unstructured":"Yu Cheng, Duo Wang, Pan Zhou, and Tao Zhang. 2017. A survey of model compression and acceleration for deep neural networks. arXiv:1710.09282. Retrieved from https:\/\/arxiv.org\/abs\/1710.09282.","journal-title":"arXiv:1710.09282"},{"key":"e_1_3_1_9_2","article-title":"Binarized neural networks: Training deep neural networks with weights and activations constrained to+ 1 or-1","author":"Courbariaux Matthieu","year":"2016","unstructured":"Matthieu Courbariaux, Itay Hubara, Daniel Soudry, Ran El-Yaniv, and Yoshua Bengio. 2016. Binarized neural networks: Training deep neural networks with weights and activations constrained to+ 1 or-1. arXiv:1602.02830. Retrieved from https:\/\/arxiv.org\/abs\/1602.02830.","journal-title":"arXiv:1602.02830"},{"key":"e_1_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.5555\/2968826.2968968"},{"key":"e_1_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/2508363.2508376"},{"key":"e_1_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2439281"},{"key":"e_1_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_25"},{"key":"e_1_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2011.2179458"},{"key":"e_1_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2747127"},{"key":"e_1_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3031371"},{"key":"e_1_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.5555\/2969442.2969547"},{"key":"e_1_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.595"},{"key":"e_1_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2745099"},{"key":"e_1_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2015.2444671"},{"key":"e_1_3_1_21_2","unstructured":"Wei Gao Sam Kwong Yu Zhou and Hui Yuan. [n.d.]."},{"key":"e_1_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00085"},{"key":"e_1_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.5555\/2383894.2383927"},{"key":"e_1_3_1_24_2","first-page":"249","volume-title":"Proceedings of the 13th International Conference on Artificial Intelligence and Statistics","author":"Glorot Xavier","year":"2010","unstructured":"Xavier Glorot and Yoshua Bengio. 2010. Understanding the difficulty of training deep feedforward neural networks. In Proceedings of the 13th International Conference on Artificial Intelligence and Statistics. JMLR Workshop and Conference Proceedings, 249\u2013256."},{"key":"e_1_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00171"},{"key":"e_1_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.5555\/3157096.3157251"},{"key":"e_1_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.5555\/2969239.2969366"},{"key":"e_1_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.5555\/89851.89872"},{"key":"e_1_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00179"},{"key":"e_1_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.5555\/2987061.2987082"},{"key":"e_1_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"e_1_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_48"},{"key":"e_1_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00447"},{"key":"e_1_3_1_34_2","article-title":"Distilling the knowledge in a neural network","author":"Hinton Geoffrey","year":"2015","unstructured":"Geoffrey Hinton, Oriol Vinyals, and Jeff Dean. 2015. Distilling the knowledge in a neural network. arXiv:1503.02531. Retrieved from https:\/\/arxiv.org\/abs\/1503.02531.","journal-title":"arXiv:1503.02531"},{"key":"e_1_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-25566-3_40"},{"key":"e_1_3_1_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00286"},{"key":"e_1_3_1_37_2","article-title":"Speeding up convolutional neural networks with low rank expansions","author":"Jaderberg Max","year":"2014","unstructured":"Max Jaderberg, Andrea Vedaldi, and Andrew Zisserman. 2014. Speeding up convolutional neural networks with low rank expansions. arXiv:1405.3866. Retrieved from https:\/\/arxiv.org\/abs\/1405.3866.","journal-title":"arXiv:1405.3866"},{"key":"e_1_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2734838"},{"key":"e_1_3_1_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2881828"},{"key":"e_1_3_1_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2019.2940105"},{"key":"e_1_3_1_41_2","doi-asserted-by":"publisher","DOI":"10.1023\/A:1012771025575"},{"key":"e_1_3_1_42_2","doi-asserted-by":"publisher","DOI":"10.1145\/2980179.2980251"},{"key":"e_1_3_1_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.182"},{"key":"e_1_3_1_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.181"},{"key":"e_1_3_1_45_2","unstructured":"Diederik P. Kingma and Jimmy Ba. 2015. Adam: A method for stochastic optimization. In International Conference on Learning Representations . https:\/\/openreview.net\/forum?id=8gmWwjFyLj."},{"key":"e_1_3_1_46_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.618"},{"key":"e_1_3_1_47_2","doi-asserted-by":"publisher","DOI":"10.5555\/109230.109298"},{"key":"e_1_3_1_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539854"},{"key":"e_1_3_1_49_2","unstructured":"Hao Li Asim Kadav Igor Durdanovic Hanan Samet and Hans Peter Graf. 2017. Pruning filters for efficient ConvNets. In International Conference on Learning Representations . https:\/\/openreview.net\/forum?id=rJqFGTslg."},{"key":"e_1_3_1_50_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2872876"},{"key":"e_1_3_1_51_2","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413523"},{"key":"e_1_3_1_52_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.151"},{"key":"e_1_3_1_53_2","doi-asserted-by":"publisher","DOI":"10.5555\/3016387.3016404"},{"key":"e_1_3_1_54_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01152"},{"key":"e_1_3_1_55_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2013.2268939"},{"key":"e_1_3_1_56_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.499"},{"key":"e_1_3_1_57_2","unstructured":"Abhilash Sunder Raj Michael Lowney Raj Shah and Gordon Wetzstein. 2020. The stanford lytro light field archive. Retrieved on Sept. 1 2020 from http:\/\/lightfields.stanford.edu\/LF2016.html."},{"key":"e_1_3_1_58_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.355"},{"key":"e_1_3_1_59_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638949"},{"key":"e_1_3_1_60_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"e_1_3_1_61_2","doi-asserted-by":"publisher","DOI":"10.1145\/2682631"},{"key":"e_1_3_1_62_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00499"},{"key":"e_1_3_1_63_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.246"},{"key":"e_1_3_1_64_2","article-title":"Convolutional neural networks with low-rank regularization","author":"Tai Cheng","year":"2015","unstructured":"Cheng Tai, Tong Xiao, Yi Zhang, Xiaogang Wang, et\u00a0al. 2015. Convolutional neural networks with low-rank regularization. arXiv:1511.06067. Retrieved from https:\/\/arxiv.org\/abs\/1511.06067.","journal-title":"arXiv:1511.06067"},{"key":"e_1_3_1_65_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.298"},{"key":"e_1_3_1_66_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00293"},{"key":"e_1_3_1_67_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.514"},{"key":"e_1_3_1_68_2","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2738617"},{"key":"e_1_3_1_69_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2653101"},{"key":"e_1_3_1_70_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33715-4_44"},{"key":"e_1_3_1_71_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.147"},{"key":"e_1_3_1_72_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.178"},{"key":"e_1_3_1_73_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2015.17"},{"key":"e_1_3_1_74_2","doi-asserted-by":"publisher","DOI":"10.1145\/3126908.3126912"},{"key":"e_1_3_1_75_2","article-title":"AutoSlim: Towards one-shot architecture search for channel numbers","author":"Yu Jiahui","year":"2019","unstructured":"Jiahui Yu and Thomas Huang. 2019. AutoSlim: Towards one-shot architecture search for channel numbers. arXiv:1903.11728. Retrieved from https:\/\/arxiv.org\/abs\/1903.11728.","journal-title":"arXiv:1903.11728"},{"key":"e_1_3_1_76_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2477682"},{"key":"e_1_3_1_77_2","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2016.2532329"},{"key":"e_1_3_1_78_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2014.2367356"},{"key":"e_1_3_1_79_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299004"},{"key":"e_1_3_1_80_2","unstructured":"Aojun Zhou Anbang Yao Yiwen Guo Lin Xu and Yurong Chen. 2017. Incremental network quantization: Towards lossless CNNs with low-precision weights. In International Conference on Learning Representations . https:\/\/openreview.net\/forum?id=HyQJ-mclg."}],"container-title":["ACM Transactions on Multimedia Computing, Communications, and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3459098","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3459098","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:47:02Z","timestamp":1750193222000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3459098"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,11,12]]},"references-count":79,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2021,11,30]]}},"alternative-id":["10.1145\/3459098"],"URL":"https:\/\/doi.org\/10.1145\/3459098","relation":{},"ISSN":["1551-6857","1551-6865"],"issn-type":[{"value":"1551-6857","type":"print"},{"value":"1551-6865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,11,12]]},"assertion":[{"value":"2020-10-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-03-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-11-12","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}