{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:40:24Z","timestamp":1777657224291,"version":"3.51.4"},"reference-count":76,"publisher":"Association for Computing Machinery (ACM)","issue":"6","license":[{"start":{"date-parts":[[2018,12,4]],"date-time":"2018-12-04T00:00:00Z","timestamp":1543881600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Graph."],"published-print":{"date-parts":[[2018,12,31]]},"abstract":"<jats:p>\n            Addressing vergence-accommodation conflict in head-mounted displays (HMDs) requires resolving two interrelated problems. First, the hardware must support viewing sharp imagery over the full accommodation range of the user. Second, HMDs should accurately reproduce retinal defocus blur to correctly drive accommodation. A multitude of\n            <jats:italic>accommodation-supporting<\/jats:italic>\n            HMDs have been proposed, with three architectures receiving particular attention: varifocal, multifocal, and light field displays. These designs all extend depth of focus, but rely on computationally expensive rendering and optimization algorithms to reproduce accurate defocus blur (often limiting content complexity and interactive applications). To date, no unified framework has been proposed to support driving these emerging HMDs using commodity content. In this paper, we introduce\n            <jats:italic>DeepFocus<\/jats:italic>\n            , a generic, end-to-end convolutional neural network designed to efficiently solve the full range of computational tasks for accommodation-supporting HMDs. This network is demonstrated to accurately synthesize defocus blur, focal stacks, multilayer decompositions, and multiview imagery using only commonly available RGB-D images, enabling real-time, near-correct depictions of retinal blur with a broad set of accommodation-supporting HMDs.\n          <\/jats:p>","DOI":"10.1145\/3272127.3275032","type":"journal-article","created":{"date-parts":[[2018,11,28]],"date-time":"2018-11-28T19:16:10Z","timestamp":1543432570000},"page":"1-13","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":48,"title":["DeepFocus"],"prefix":"10.1145","volume":"37","author":[{"given":"Lei","family":"Xiao","sequence":"first","affiliation":[{"name":"Facebook Reality Labs"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anton","family":"Kaplanyan","sequence":"additional","affiliation":[{"name":"Facebook Reality Labs"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexander","family":"Fix","sequence":"additional","affiliation":[{"name":"Facebook Reality Labs"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Matthew","family":"Chapman","sequence":"additional","affiliation":[{"name":"Facebook Reality Labs"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Douglas","family":"Lanman","sequence":"additional","affiliation":[{"name":"Facebook Reality Labs"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2018,12,4]]},"reference":[{"key":"e_1_2_2_1_1","unstructured":"Mart\u00edn Abadi et al. 2015. TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems. https:\/\/www.tensorflow.org\/  Mart\u00edn Abadi et al. 2015. TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems. https:\/\/www.tensorflow.org\/"},{"key":"e_1_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3130800.3130892"},{"key":"e_1_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/1015706.1015804"},{"key":"e_1_2_2_4_1","volume-title":"Kosloff","author":"Barsky Brian A.","year":"2008","unstructured":"Brian A. Barsky and Todd J . Kosloff . 2008 . Algorithms for Rendering Depth of Field Effects in Computer Graphics. In Proc. ICCOMP. 999--1010. Brian A. Barsky and Todd J. Kosloff. 2008. Algorithms for Rendering Depth of Field Effects in Computer Graphics. In Proc. ICCOMP. 999--1010."},{"key":"e_1_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1108491108"},{"key":"e_1_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073601"},{"key":"e_1_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/2487228.2487238"},{"key":"e_1_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3130800.3130815"},{"key":"e_1_2_2_9_1","volume-title":"Fast and accurate deep network learning by exponential linear units (elus). arXiv preprint arXiv:1511.07289","author":"Clevert Djork-Arn\u00e9","year":"2015","unstructured":"Djork-Arn\u00e9 Clevert , Thomas Unterthiner , and Sepp Hochreiter . 2015. Fast and accurate deep network learning by exponential linear units (elus). arXiv preprint arXiv:1511.07289 ( 2015 ). Djork-Arn\u00e9 Clevert, Thomas Unterthiner, and Sepp Hochreiter. 2015. Fast and accurate deep network learning by exponential linear units (elus). arXiv preprint arXiv:1511.07289 (2015)."},{"key":"e_1_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/964965.808590"},{"key":"e_1_2_2_11_1","volume-title":"Depth of Field: A Survey of Techniques","author":"Demers Joe","unstructured":"Joe Demers . 2004. Depth of Field: A Survey of Techniques . In GPU Gems, Randima Fernando (Ed.). Addison-Wesley , 375--390. Joe Demers. 2004. Depth of Field: A Survey of Techniques. In GPU Gems, Randima Fernando (Ed.). Addison-Wesley, 375--390."},{"key":"e_1_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/2508363.2508376"},{"key":"e_1_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2017.2657058"},{"key":"e_1_2_2_14_1","volume-title":"Proc. CVPR. 5515--5524","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's Imagery . In Proc. CVPR. 5515--5524 . John Flynn, Ivan Neulander, James Philbin, and Noah Snavely. 2016. DeepStereo: Learning to Predict New Views From the World's Imagery. In Proc. CVPR. 5515--5524."},{"key":"e_1_2_2_15_1","volume-title":"Proc. Artificial Intelligence and Statistics. 249--256","author":"Glorot Xavier","year":"2010","unstructured":"Xavier Glorot and Yoshua Bengio . 2010 . Understanding the difficulty of training deep feedforward neural networks . In Proc. Artificial Intelligence and Statistics. 249--256 . Xavier Glorot and Yoshua Bengio. 2010. Understanding the difficulty of training deep feedforward neural networks. In Proc. Artificial Intelligence and Statistics. 249--256."},{"key":"e_1_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/97880.97913"},{"key":"e_1_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_2_2_18_1","volume-title":"Banks","author":"Held Robert T.","year":"2012","unstructured":"Robert T. Held , Emily A. Cooper , and Martin S . Banks . 2012 . Blur and Disparity Are Complementary Cues to Depth . Current Biology 22 (2012). Issue 5. Robert T. Held, Emily A. Cooper, and Martin S. Banks. 2012. Blur and Disparity Are Complementary Cues to Depth. Current Biology 22 (2012). Issue 5."},{"key":"e_1_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/1731047.1731057"},{"key":"e_1_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1167\/8.3.33"},{"key":"e_1_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1364\/OE.22.013896"},{"key":"e_1_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1364\/OE.22.013484"},{"key":"e_1_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/2766922"},{"key":"e_1_2_2_24_1","volume-title":"Proc. ICML. 448--456","author":"Ioffe Sergey","year":"2015","unstructured":"Sergey Ioffe and Christian Szegedy . 2015 . Batch normalization: Accelerating deep network training by reducing internal covariate shift . In Proc. ICML. 448--456 . Sergey Ioffe and Christian Szegedy. 2015. Batch normalization: Accelerating deep network training by reducing internal covariate shift. In Proc. ICML. 448--456."},{"key":"e_1_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/2980179.2980251"},{"key":"e_1_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073617"},{"key":"e_1_2_2_27_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba . 2014 . Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014). Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/2858036.2858140"},{"key":"e_1_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073594"},{"key":"e_1_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073622"},{"key":"e_1_2_2_31_1","first-page":"1912","article-title":"Resolving the Vergence-Accommodation Conflict in Head-Mounted Displays","volume":"22","author":"Kramida Gregory","year":"2016","unstructured":"Gregory Kramida . 2016 . Resolving the Vergence-Accommodation Conflict in Head-Mounted Displays . IEEE TVCG 22 , 7 (2016), 1912 -- 1931 . Gregory Kramida. 2016. Resolving the Vergence-Accommodation Conflict in Head-Mounted Displays. IEEE TVCG 22, 7 (2016), 1912--1931.","journal-title":"IEEE TVCG"},{"key":"e_1_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CGI.2003.1214466"},{"key":"e_1_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/2508363.2508366"},{"key":"e_1_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/1618452.1618480"},{"key":"e_1_2_2_35_1","volume-title":"Gerard Jounghyun Kim, and Seungmoon Choi","author":"Lee Sungkil","year":"2008","unstructured":"Sungkil Lee , Gerard Jounghyun Kim, and Seungmoon Choi . 2008 . Real-time depth-of-field rendering using point splatting on per-pixel layers. In Computer Graphics Forum, Vol. 27 . Wiley Online Library , 1955--1962. Sungkil Lee, Gerard Jounghyun Kim, and Seungmoon Choi. 2008. Real-time depth-of-field rendering using point splatting on per-pixel layers. In Computer Graphics Forum, Vol. 27. Wiley Online Library, 1955--1962."},{"key":"e_1_2_2_36_1","volume-title":"A systematic method for designing depth-fused multi-focal plane three-dimensional displays. Optics express 18, 11","author":"Liu Sheng","year":"2010","unstructured":"Sheng Liu and Hong Hua . 2010. A systematic method for designing depth-fused multi-focal plane three-dimensional displays. Optics express 18, 11 ( 2010 ), 11562--11573. Sheng Liu and Hong Hua. 2010. A systematic method for designing depth-fused multi-focal plane three-dimensional displays. Optics express 18, 11 (2010), 11562--11573."},{"key":"e_1_2_2_37_1","volume-title":"Banks","author":"Love Gordon D.","year":"2009","unstructured":"Gordon D. Love , David M. Hoffman , Philip J.W. Hands , James Gao , Andrew K. Kirby , and Martin S . Banks . 2009 . High-speed switchable lens enables the development of a volumetric stereoscopic display. Optics Express 17, 18 (2009). Gordon D. Love, David M. Hoffman, Philip J.W. Hands, James Gao, Andrew K. Kirby, and Martin S. Banks. 2009. High-speed switchable lens enables the development of a volumetric stereoscopic display. Optics Express 17, 18 (2009)."},{"key":"e_1_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073624"},{"key":"e_1_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/2010324.1964935"},{"key":"e_1_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cag.2013.10.003"},{"key":"e_1_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073590"},{"key":"e_1_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/2556288.2557089"},{"key":"e_1_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3130800.3130846"},{"key":"e_1_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.13225"},{"key":"e_1_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/2766909"},{"key":"e_1_2_2_46_1","first-page":"337","article-title":"Spatial-light-modulator-based three-dimensional multiplanar display","volume":"3012","author":"Neil Mark A. A.","year":"1997","unstructured":"Mark A. A. Neil , Edward G. S. Paige , and Leon O. D. Sucharov . 1997 . Spatial-light-modulator-based three-dimensional multiplanar display . SPIE 3012 (1997), 337 -- 341 . Mark A. A. Neil, Edward G. S. Paige, and Leon O. D. Sucharov. 1997. Spatial-light-modulator-based three-dimensional multiplanar display. SPIE 3012 (1997), 337--341.","journal-title":"SPIE"},{"key":"e_1_2_2_47_1","unstructured":"Nvidia Corporation. 2017--2018. TensorRT. https:\/\/developer.nvidia.com\/tensorrt.  Nvidia Corporation. 2017--2018. TensorRT. https:\/\/developer.nvidia.com\/tensorrt."},{"key":"e_1_2_2_48_1","volume-title":"Optimizing virtual reality for all users through gaze-contingent and adaptive focus displays. PNAS 114, 9","author":"Padmanaban Nitish","year":"2017","unstructured":"Nitish Padmanaban , Robert Konrad , Tal Stramer , Emily A. Cooper , and Gordon Wetzstein . 2017. Optimizing virtual reality for all users through gaze-contingent and adaptive focus displays. PNAS 114, 9 ( 2017 ). Nitish Padmanaban, Robert Konrad, Tal Stramer, Emily A. Cooper, and Gordon Wetzstein. 2017. Optimizing virtual reality for all users through gaze-contingent and adaptive focus displays. PNAS 114, 9 (2017)."},{"key":"e_1_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.278"},{"key":"e_1_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"e_1_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/2699276.2699288"},{"key":"e_1_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/2682631"},{"key":"e_1_2_2_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.207"},{"key":"e_1_2_2_54_1","doi-asserted-by":"publisher","DOI":"10.1167\/11.8.11"},{"key":"e_1_2_2_55_1","volume-title":"Proc. Graphics Interface. 59--66","author":"Shinya M.","year":"1994","unstructured":"M. Shinya . 1994 . Post-filtering for Depth of Field Simulation with Ray Distribution Buffer . In Proc. Graphics Interface. 59--66 . M. Shinya. 1994. Post-filtering for Depth of Field Simulation with Ray Distribution Buffer. In Proc. Graphics Interface. 59--66."},{"key":"e_1_2_2_56_1","doi-asserted-by":"publisher","DOI":"10.1889\/1.1987395"},{"key":"e_1_2_2_57_1","unstructured":"Side Effects. 1996--2018. Houdini. http:\/\/www.sidefx.com\/.  Side Effects. 1996--2018. Houdini. http:\/\/www.sidefx.com\/."},{"key":"e_1_2_2_58_1","doi-asserted-by":"publisher","DOI":"10.1364\/JOSA.64.001512"},{"key":"e_1_2_2_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.246"},{"key":"e_1_2_2_60_1","doi-asserted-by":"publisher","DOI":"10.1145\/3130800.3130807"},{"key":"e_1_2_2_61_1","unstructured":"Unity Technologies. 2005--2018. Unity Engine. http:\/\/unity3d.com.  Unity Technologies. 2005--2018. Unity Engine. http:\/\/unity3d.com."},{"key":"e_1_2_2_62_1","unstructured":"The Foundry. 1993--2018. NUKE. https:\/\/www.foundry.com\/products\/nuke.  The Foundry. 1993--2018. NUKE. https:\/\/www.foundry.com\/products\/nuke."},{"key":"e_1_2_2_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"e_1_2_2_65_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.147"},{"key":"e_1_2_2_66_1","doi-asserted-by":"publisher","DOI":"10.1117\/12.908883"},{"key":"e_1_2_2_67_1","doi-asserted-by":"publisher","DOI":"10.1145\/2185520.2185576"},{"key":"e_1_2_2_68_1","doi-asserted-by":"publisher","DOI":"10.1145\/2790060.2790069"},{"key":"e_1_2_2_69_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.178"},{"key":"e_1_2_2_70_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2016.7552965"},{"key":"e_1_2_2_71_1","doi-asserted-by":"publisher","DOI":"10.1155\/2016\/4125909"},{"key":"e_1_2_2_72_1","volume-title":"Multi-scale context aggregation by dilated convolutions. arXiv preprint arXiv:1511.07122","author":"Yu Fisher","year":"2015","unstructured":"Fisher Yu and Vladlen Koltun . 2015. Multi-scale context aggregation by dilated convolutions. arXiv preprint arXiv:1511.07122 ( 2015 ). Fisher Yu and Vladlen Koltun. 2015. Multi-scale context aggregation by dilated convolutions. arXiv preprint arXiv:1511.07122 (2015)."},{"key":"e_1_2_2_73_1","volume-title":"Proc. ICLR.","author":"Yu Fisher","year":"2016","unstructured":"Fisher Yu and Vladlen Koltun . 2016 . Multi-Scale Context Aggregation by Dilated Convolutions . In Proc. ICLR. Fisher Yu and Vladlen Koltun. 2016. Multi-Scale Context Aggregation by Dilated Convolutions. In Proc. ICLR."},{"key":"e_1_2_2_74_1","doi-asserted-by":"publisher","DOI":"10.1167\/16.6.17"},{"key":"e_1_2_2_75_1","doi-asserted-by":"publisher","DOI":"10.1167\/16.6.17"},{"key":"e_1_2_2_76_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.300"},{"key":"e_1_2_2_77_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299004"}],"container-title":["ACM Transactions on Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3272127.3275032","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3272127.3275032","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T00:44:04Z","timestamp":1750207444000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3272127.3275032"}},"subtitle":["learned image synthesis for computational displays"],"short-title":[],"issued":{"date-parts":[[2018,12,4]]},"references-count":76,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2018,12,31]]}},"alternative-id":["10.1145\/3272127.3275032"],"URL":"https:\/\/doi.org\/10.1145\/3272127.3275032","relation":{},"ISSN":["0730-0301","1557-7368"],"issn-type":[{"value":"0730-0301","type":"print"},{"value":"1557-7368","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,12,4]]},"assertion":[{"value":"2018-12-04","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}