{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T15:48:38Z","timestamp":1782748118309,"version":"3.54.5"},"reference-count":38,"publisher":"Association for Computing Machinery (ACM)","issue":"4","license":[{"start":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T00:00:00Z","timestamp":1782691200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["Proc. ACM Comput. Graph. Interact. Tech."],"published-print":{"date-parts":[[2026,7,1]]},"abstract":"<jats:p>Radiance fields, including their recent efficient forms such as 3D Gaussian Splatting and Sparse Voxels, have revolutionized photorealistic 3D scene visualization by enabling high-fidelity reconstruction of complex environments, making them a natural match for light field displays. However, integrating these technologies presents significant computational challenges, as light field displays require many high-resolution renderings from slightly shifted viewpoints, while radiance fields rely on computationally intensive volume rendering, which is intractable to achieve real-time speeds even with efficient scene representations. In this paper, we propose a unified and efficient framework for real-time radiance field rendering on light field displays. Rather than re-rendering each view independently, our method converts the input radiance field into shared intermediate sweeping planes that can be efficiently composited into dense light-field views in a single pass. Our method prioritizes shared, non-directional plane caching for real-time performance, trading fine view-dependent color effects for a modest increase in intermediate memory usage. Our framework generalizes across different scene representations without retraining and avoids repeated computation across views. We further demonstrate a real-time interactive application on a Looking Glass display, achieving 200+ FPS at 512p across 45 rendered views and enabling seamless, immersive 3D interactive viewing experiences. On standard benchmarks, our method achieves up to 22\u00d7 speedup compared to independently rendering each view, while largely preserving image quality.<\/jats:p>","DOI":"10.1145\/3820023","type":"journal-article","created":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T15:37:39Z","timestamp":1782747459000},"page":"1-19","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Real-time 3D Visualization of Radiance Fields on Light Field Displays 56"],"prefix":"10.1145","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1197-368X","authenticated-orcid":false,"given":"Jonghyun","family":"Kim","sequence":"first","affiliation":[{"name":"NVIDIA","place":["Santa Clara, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8910-4524","authenticated-orcid":false,"given":"Cheng","family":"Sun","sequence":"additional","affiliation":[{"name":"NVIDIA","place":["Santa Clara, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-6234-936X","authenticated-orcid":false,"given":"Michael","family":"Stengel","sequence":"additional","affiliation":[{"name":"Nvidia","place":["Santa Clara, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-1704-1013","authenticated-orcid":false,"given":"Matthew","family":"Chan","sequence":"additional","affiliation":[{"name":"nvidia","place":["Santa Clara, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-0820-115X","authenticated-orcid":false,"given":"Andrew","family":"Russell","sequence":"additional","affiliation":[{"name":"NVIDIA","place":["Santa Clara, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5709-6045","authenticated-orcid":false,"given":"Jaehyun","family":"Jung","sequence":"additional","affiliation":[{"name":"NVIDIA","place":["Santa Clara, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-1741-0748","authenticated-orcid":false,"given":"Wil","family":"Braithwaite","sequence":"additional","affiliation":[{"name":"NVIDIA","place":["Santa Clara, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8206-5785","authenticated-orcid":false,"given":"David","family":"Luebke","sequence":"additional","affiliation":[{"name":"NVIDIA","place":["Santa Clara, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-0213-2860","authenticated-orcid":false,"given":"Shalini","family":"De Mello","sequence":"additional","affiliation":[{"name":"NVIDIA","place":["Santa Clara, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,29]]},"reference":[{"key":"e_1_3_3_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00539"},{"key":"e_1_3_3_3_1","doi-asserted-by":"publisher","unstructured":"Michael\u00a0J. Broxton John Flynn Ryan Overbeck Daniel Erickson Peter Hedman Matthew Duvall Jason Dourgarian Jay Busch Matt Whalen and Paul Debevec. 2020. Immersive Light Field Video with a Layered Mesh Representation. ACM Trans. Graph. 39 4 (2020) 86:1\u201386:15. doi:10.1145\/3386569.3392485","DOI":"10.1145\/3386569.3392485"},{"key":"e_1_3_3_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/383259.383309"},{"key":"e_1_3_3_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19824-3_21"},{"key":"e_1_3_3_6_1","doi-asserted-by":"crossref","unstructured":"Shuo Chen Binbin Yan Xinzhu Sang Duo Chen Peng Wang Zeyuan Yang Xiao Guo and Chongli Zhong. 2022b. Fast virtual view synthesis for an 8k 3d light-field display based on cutoff-nerf and 3d voxel rendering. Optics Express 30 24 (2022) 44201\u201344217.","DOI":"10.1364\/OE.473852"},{"key":"e_1_3_3_7_1","doi-asserted-by":"publisher","DOI":"10.1117\/12.524762"},{"key":"e_1_3_3_8_1","doi-asserted-by":"crossref","unstructured":"Laura Fink Svenja Strobel Linus Franke and Marc Stamminger. 2023. Efficient rendering for light field displays using tailored projective mappings. Proceedings of the ACM on Computer Graphics and Interactive Techniques 6 1 (2023) 1\u201317.","DOI":"10.1145\/3585498"},{"key":"e_1_3_3_9_1","unstructured":"Google Inc.2026. Google. https:\/\/google.com\/ Accessed: March 2026."},{"key":"e_1_3_3_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/1174429.1174479"},{"key":"e_1_3_3_11_1","unstructured":"Thomas H\u00fcbner Yanci Zhang and Renato Pajarola. 2007. Single-Pass Multi-View Rendering. IADIS Int. J. on Computer Science and Information Systems 2 2 (2007) 122\u2013140."},{"key":"e_1_3_3_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/344779.344929"},{"key":"e_1_3_3_13_1","doi-asserted-by":"crossref","unstructured":"Herbert\u00a0E Ives. 1931. Optical properties of a Lippmann lenticulated sheet. JOSA 21 3 (1931) 171\u2013176.","DOI":"10.1364\/JOSA.21.000171"},{"key":"e_1_3_3_14_1","doi-asserted-by":"crossref","unstructured":"Luyu Ji Xinzhu Sang Shujun Xing Xunbo Yu Binbin Yan and Jiahui Yang. 2025. Text-driven light-field content editing for three-dimensional light-field display based on Gaussian splatting. Optics Express 33 1 (2025) 954\u2013971.","DOI":"10.1364\/OE.547233"},{"key":"e_1_3_3_15_1","doi-asserted-by":"crossref","unstructured":"Bernhard Kerbl Georgios Kopanas Thomas Leimk\u00fchler and George Drettakis. 2023. 3d gaussian splatting for real-time radiance field rendering. ACM Trans. Graph. 42 4 (2023) 139\u20131.","DOI":"10.1145\/3592433"},{"key":"e_1_3_3_16_1","doi-asserted-by":"crossref","unstructured":"Jonghyun Kim Chang-Kun Lee Jong-Young Hong Changwon Jang Youngmo Jeong Jiwoon Yeom and Byoungho Lee. 2015. Calibration method for the panel-type multi-view display. Journal of the Optical Society of Korea 19 5 (2015) 477\u2013486.","DOI":"10.3807\/JOSK.2015.19.5.477"},{"key":"e_1_3_3_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3757373.3763771"},{"key":"e_1_3_3_18_1","unstructured":"Joonsoo Kim Kugjin Yun Hyon-Gon Choo Hyeongju Mun and Kyeongbo Kong. 2026. 3D Gaussian rasterization for direct rendering of view-multiplexed images on multiview displays. ETRI Journal (2026)."},{"key":"e_1_3_3_19_1","doi-asserted-by":"crossref","unstructured":"Douglas Lanman Matthew Hirsch Yunhee Kim and Ramesh Raskar. 2010. Content-adaptive parallax barriers: optimizing dual-layer 3D displays using low-rank light field factorization. ACM Transactions on Graphics (TOG) 29 6 (2010) 1\u201310.","DOI":"10.1145\/1882261.1866164"},{"key":"e_1_3_3_20_1","unstructured":"Leia Inc.2025. Leia Official Website. https:\/\/www.leiainc.com\/ Accessed: January 2025."},{"key":"e_1_3_3_21_1","unstructured":"Looking Glass Factory Inc.2026. Looking Glass Factory Official Website. https:\/\/lookingglassfactory.com\/ Accessed: March 2026."},{"key":"e_1_3_3_22_1","doi-asserted-by":"crossref","unstructured":"Ben Mildenhall Pratul\u00a0P Srinivasan Matthew Tancik Jonathan\u00a0T Barron Ravi Ramamoorthi and Ren Ng. 2021. Nerf: Representing scenes as neural radiance fields for view synthesis. Commun. ACM 65 1 (2021) 99\u2013106.","DOI":"10.1145\/3503250"},{"key":"e_1_3_3_23_1","doi-asserted-by":"crossref","unstructured":"Thomas M\u00fcller Alex Evans Christoph Schied and Alexander Keller. 2022. Instant neural graphics primitives with a multiresolution hash encoding. ACM transactions on graphics (TOG) 41 4 (2022) 1\u201315.","DOI":"10.1145\/3528223.3530127"},{"key":"e_1_3_3_24_1","unstructured":"NVIDIA Corporation. 2025. VRWorks - Multi-View Rendering (MVR). https:\/\/developer.nvidia.com\/vrworks\/graphics\/multiview Accessed: May 2025."},{"key":"e_1_3_3_25_1","doi-asserted-by":"crossref","unstructured":"S\u00e9dick Rabia Guillaume Allain Rosalie Tremblay and Simon Thibault. 2024. Orthoscopic elemental image synthesis for 3D light field display using lens design software and real-world captured neural radiance field. Optics Express 32 5 (2024) 7800\u20137815.","DOI":"10.1364\/OE.510579"},{"key":"e_1_3_3_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01408"},{"key":"e_1_3_3_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/280814.280882"},{"key":"e_1_3_3_28_1","unstructured":"Sony Electronics Inc.2025. Spatial Reality Display by Sony. https:\/\/pro.sony\/ue_US\/products\/spatial-reality-displays\/3d-professional-images Accessed: January 2025."},{"key":"e_1_3_3_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3588037.3595385"},{"key":"e_1_3_3_30_1","unstructured":"Cheng Sun Jaesung Choe Charles Loop Wei-Chiu Ma and Yu-Chiang\u00a0Frank Wang. 2024. Sparse Voxels Rasterization: Real-time High-fidelity Radiance Field Rendering. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2412.04459 (2024)."},{"key":"e_1_3_3_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00538"},{"key":"e_1_3_3_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01120"},{"key":"e_1_3_3_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591516"},{"key":"e_1_3_3_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00984"},{"key":"e_1_3_3_35_1","first-page":"13","volume-title":"EGPGV@ Eurographics\/EuroVis","author":"Unterguggenberger Johannes","year":"2020","unstructured":"Johannes Unterguggenberger, Bernhard Kerbl, Markus Steinberger, Dieter Schmalstieg, and Michael Wimmer. 2020. Fast Multi-View Rendering for Real-Time Applications.. In EGPGV@ Eurographics\/EuroVis. 13\u201323."},{"key":"e_1_3_3_36_1","doi-asserted-by":"publisher","DOI":"10.1117\/12.349368"},{"key":"e_1_3_3_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00843"},{"key":"e_1_3_3_38_1","doi-asserted-by":"crossref","unstructured":"Zongyuan Yang Baolin Liu Yingde Song Lan Yi Yongping Xiong Zhaohe Zhang and Xunbo Yu. 2024. DirectL: Efficient Radiance Fields Rendering for 3D Light Field Displays. ACM Transactions on Graphics (TOG) 43 6 (2024) 1\u201319.","DOI":"10.1145\/3687897"},{"key":"e_1_3_3_39_1","doi-asserted-by":"crossref","unstructured":"Tinghui Zhou Richard Tucker John Flynn Graham Fyffe and Noah Snavely. 2018. Stereo magnification: learning view synthesis using multiplane images. ACM Transactions on Graphics (TOG) 37 4 (2018) 1\u201312.","DOI":"10.1145\/3197517.3201323"}],"container-title":["Proceedings of the ACM on Computer Graphics and Interactive Techniques"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3820023","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T15:43:37Z","timestamp":1782747817000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3820023"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,29]]},"references-count":38,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2026,7,1]]}},"alternative-id":["10.1145\/3820023"],"URL":"https:\/\/doi.org\/10.1145\/3820023","relation":{},"ISSN":["2577-6193"],"issn-type":[{"value":"2577-6193","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,29]]},"assertion":[{"value":"2026-06-29","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}