{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T06:10:13Z","timestamp":1784268613745,"version":"3.55.0"},"reference-count":65,"publisher":"Wiley","license":[{"start":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T00:00:00Z","timestamp":1774828800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"},{"start":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T00:00:00Z","timestamp":1774828800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["#2225861"],"award-info":[{"award-number":["#2225861"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Computer Graphics Forum"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    Image processing techniques can be used to modulate the pixel intensities of an image to reduce the power consumption of the display device. A simple example of this consists of uniformly dimming the entire image. Such algorithms should strive to minimize the impact on image quality while maximizing power savings. Techniques based on heuristics or human perception have been proposed, both for traditional flat panel displays and modern display modalities such as virtual and augmented reality (VR\/AR). In this paper, we focus on developing and evaluating display power\u2010saving techniques that use machine learning (ML) in VR displays. We developed a U\u2010Net\u2010based technique paired with perceptual and power optimization loss functions that generates spatially varying dimming maps. These dimming maps are used to modulate input images, per\u2010pixel, to generate a power\u2010efficient image. Our pipeline was validated via quantitative analysis using image quality metrics and through a subjective study. Our subjective validation provides results scaled in perceptual just\u2010objectionable\u2010difference (JOD) units. This data, when rescaled, allows for comparisons of our technique with recent studies on VR display power optimization. Our results show that participants prefer our technique over a uniform dimming baseline for high target power saving conditions. This model and study serve as a template and baseline for future applications of deep learning to display power optimization. Model training code and data can be found at\n                    <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" xlink:href=\"http:\/\/kenchen10.github.io\/projects\/mlpea\/index.html\">kenchen10.github.io\/projects\/mlpea\/index.html<\/jats:ext-link>\n                    .\n                  <\/jats:p>","DOI":"10.1111\/cgf.70369","type":"journal-article","created":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T12:54:09Z","timestamp":1774875249000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["ML\u2010PEA: Machine Learning\u2010Based Perceptual Algorithms for Display Power Optimization"],"prefix":"10.1111","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8095-4407","authenticated-orcid":false,"given":"Kenneth","family":"Chen","sequence":"first","affiliation":[{"name":"New York University  USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-0697-7672","authenticated-orcid":false,"given":"Nathan","family":"Matsuda","sequence":"additional","affiliation":[{"name":"Meta Reality Labs  USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-4320-7548","authenticated-orcid":false,"given":"Thomas","family":"Wan","sequence":"additional","affiliation":[{"name":"Meta Reality Labs  USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6962-1687","authenticated-orcid":false,"given":"Ajit","family":"Ninan","sequence":"additional","affiliation":[{"name":"Meta Reality Labs  USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7367-0131","authenticated-orcid":false,"given":"Alexandre","family":"Chapiro","sequence":"additional","affiliation":[{"name":"Meta Reality Labs  USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3094-5844","authenticated-orcid":false,"given":"Qi","family":"Sun","sequence":"additional","affiliation":[{"name":"New York University  USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,3,30]]},"reference":[{"key":"e_1_2_9_2_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73226-3_9"},{"key":"e_1_2_9_3_2","doi-asserted-by":"crossref","unstructured":"Adi Nugroho KuntoroandRuan Shanq-Jang. \u201cR-ACE Network for OLED Image Power Saving\u201d.2022 IEEE 4th Global Conference on Life Sciences and Technologies (LifeTech).2022 284\u2013285. doi:10.1109\/LifeTech53646.2022.97547483.","DOI":"10.1109\/LifeTech53646.2022.9754748"},{"key":"e_1_2_9_4_2","doi-asserted-by":"crossref","unstructured":"Agustsson EirikurandTimofte Radu. \u201cNtire 2017 challenge on single image super-resolution: Dataset and study\u201d.Proceedings of the IEEE conference on computer vision and pattern recognition workshops.2017 126\u20131354.","DOI":"10.1109\/CVPRW.2017.150"},{"key":"e_1_2_9_5_2","doi-asserted-by":"publisher","DOI":"10.1145\/1999995.2000002"},{"key":"e_1_2_9_5_3","unstructured":"url:https:\/\/doi.org\/10.1145\/1999995.20000021."},{"key":"e_1_2_9_6_2","unstructured":"Cadenas Cesar. \u201cThe Quest 3 is getting a personal assistant courtesy of Meta AI\u201d.TechRadar(2024). url:https:\/\/www.techradar.com\/computing\/virtual-reality-augmented-reality\/the-quest-3-is-getting-a-personal-assistant-courtesy-of-meta-ai?utm_source=chatgpt.com8."},{"key":"e_1_2_9_7_2","doi-asserted-by":"crossref","unstructured":"Chen Kenneth Duinkharjav Budmonde Ujjainkar Nisarg et al. \u201cImperceptible Color Modulation for Power Saving in VR\/AR\u201d.ACM SIGGRAPH 2023 Emerging Technologies. SIGGRAPH '23.2023. url:https:\/\/doi.org\/10.1145\/3588037.35953882.","DOI":"10.1145\/3588037.3595388"},{"key":"e_1_2_9_8_2","first-page":"11285","article-title":"Tinytl: Reduce memory, not parameters for efficient on-device learning","volume":"33","author":"Cai Han","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_9_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/3721238.3730629"},{"key":"e_1_2_9_9_3","unstructured":"url:https:\/\/doi.org\/10.1145\/3721238.37306293."},{"key":"e_1_2_9_10_2","doi-asserted-by":"crossref","unstructured":"Choi Inseok Shim Hojun andChang Naehyuck. \u201cLow-power color TFT LCD display for hand-held embedded systems\u201d.Proceedings of the International Symposium on Low Power Electronics and Design.2002 112\u2013117. doi:10.1109\/LPE.2002.1467222.","DOI":"10.1109\/LPE.2002.146722"},{"key":"e_1_2_9_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/3658126"},{"key":"e_1_2_9_11_3","unstructured":"url:https:\/\/doi.org\/10.1145\/36581262 3 5\u20137."},{"issue":"6","key":"e_1_2_9_12_2","first-page":"144:1","article-title":"Color-Perception-Guided Display Power Reduction for Virtual Reality","volume":"41","author":"Duinkharjav Budmonde","year":"2022","journal-title":"ACM Trans. Graph. (Proc. SIGGRAPH Asia)"},{"issue":"5","key":"e_1_2_9_13_2","first-page":"2567","article-title":"Image quality assessment: Unifying structure and texture similarity","volume":"44","author":"Ding Keyan","year":"2020","journal-title":"IEEE transactions on pattern analysis and machine intelligence"},{"key":"e_1_2_9_14_2","doi-asserted-by":"publisher","DOI":"10.1145\/1999995.2000004"},{"key":"e_1_2_9_14_3","unstructured":"url:https:\/\/doi.org\/10.1145\/1999995.20000042 3."},{"key":"e_1_2_9_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2011.167"},{"key":"e_1_2_9_16_2","doi-asserted-by":"publisher","DOI":"10.1145\/581630.581664"},{"key":"e_1_2_9_16_3","unstructured":"url:https:\/\/doi.org\/10.1145\/581630.5816642."},{"key":"e_1_2_9_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2690523"},{"key":"e_1_2_9_18_2","unstructured":"Hsiung Hao-Lun Sun1 Lei Tsung Nandhini ChandramoorthyPin-YuChen andHo Yi. \u201cNeuralFuse: Improving the Accuracy of Access-Limited Neural Network Inference in Low-Voltage Regimes\u201d.Annual Conference on Neural Information Processing Systems.20222."},{"key":"e_1_2_9_19_2","unstructured":"ITU International Telecommunication Union Radiocommunication Sector. \u201cDisplay energy reduction through image signal processing\u201d.Report ITU-R BT. 2540-0(2024) 3."},{"key":"e_1_2_9_20_2","doi-asserted-by":"crossref","unstructured":"Johnson Justin Alahi Alexandre andFei-Fei Li. \u201cPerceptual Losses for Real-Time Style Transfer and Super-Resolution\u201d.Computer Vision \u2013 ECCV 2016. Ed. by Leibe Bastian Matas Jiri Sebe Nicu and Welling Max. Cham: Springer International Publishing 2016 694\u2013711. isbn: 978-3-319-46475-6 3.","DOI":"10.1007\/978-3-319-46475-6_43"},{"key":"e_1_2_9_21_2","doi-asserted-by":"crossref","unstructured":"Jin Yize Chen Meixu Bell Todd Goodall et al. \u201cStudy of 2D foveated video quality in virtual reality\u201d.Applications of Digital Image Processing XLIII. Ed. by Tescher Andrew G. and Ebrahimi Touradj. Vol. 11510. International Society for Optics and Photonics. SPIE 2020 1151007. doi:10.1117\/12.2568883.","DOI":"10.1117\/12.2568883"},{"key":"e_1_2_9_21_3","unstructured":"url:https:\/\/doi.org\/10.1117\/12.25688836."},{"key":"e_1_2_9_22_2","unstructured":"Jin Yize Chen Meixu Goodall Todd et al. \u201cLIVE-Facebook Technologies-Compressed Virtual Reality (LIVE-FBT-FCVR) Databases\u201d. Online:http:\/\/live.ece.utexas.edu\/research\/LIVEF-BTFCVR\/index.html(2019) 6."},{"key":"e_1_2_9_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3087322"},{"key":"e_1_2_9_24_2","unstructured":"Kingma Diederik PandBa Jimmy. \u201cAdam: A method for stochastic optimization\u201d.arXiv preprint arXiv:1412.6980(2014) 4."},{"key":"e_1_2_9_25_2","doi-asserted-by":"publisher","DOI":"10.1889\/1.2408394"},{"key":"e_1_2_9_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3038428"},{"key":"e_1_2_9_27_2","doi-asserted-by":"publisher","DOI":"10.1145\/3355089.3356557"},{"key":"e_1_2_9_27_3","unstructured":"url:https:\/\/doi.org\/10.1145\/3355089.33565578."},{"issue":"1","key":"e_1_2_9_28_2","article-title":"VMAF: The journey continues","volume":"25","author":"Li Zhi","year":"2018","journal-title":"Netflix Technology Blog"},{"key":"e_1_2_9_29_2","doi-asserted-by":"crossref","unstructured":"Le Meur Olivier Demarty Claire-H\u00e9l\u00e8ne andBlonde Laurent. \u201cDeep-Learning-Based Energy Aware Images\u201d.2023 IEEE International Conference on Image Processing (ICIP).2023 590\u2013594. doi:10.1109\/ICIP49359.2023.102221883 5 11 13 14.","DOI":"10.1109\/ICIP49359.2023.10222188"},{"key":"e_1_2_9_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2011.2159387"},{"key":"e_1_2_9_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2023.3320558"},{"key":"e_1_2_9_32_2","doi-asserted-by":"publisher","DOI":"10.1145\/3658144"},{"key":"e_1_2_9_32_3","unstructured":"url:https:\/\/doi.org\/10.1145\/36581444 11 15."},{"key":"e_1_2_9_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2012.2214050"},{"key":"e_1_2_9_34_2","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-8659.2012.03188.x"},{"key":"e_1_2_9_34_3","unstructured":"eprint:https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/j.1467-8659.2012.03188.x."},{"key":"e_1_2_9_34_4","unstructured":"url:https:\/\/onlinelibrary.wiley.com\/doi\/abs\/10.1111\/j.1467-8659.2012.03188.x6."},{"key":"e_1_2_9_35_2","unstructured":"Mikhailiuk Aliaksei Wilmot Clifford Perez-Ortiz Maria et al. \u201cActive Sampling for Pairwise Comparisons via Approximate Message Passing and Information Gain Maximization\u201d.2020 IEEE International Conference on Pattern Recognition (ICPR). Jan.20216."},{"key":"e_1_2_9_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2016.2604042"},{"key":"e_1_2_9_37_2","unstructured":"Perez-Ortiz MariaandMantiuk Rafal K.\u201cA practical guide and software for analysing pairwise comparison experiments\u201d.arXiv preprint arXiv:1712.03686(2017) 6 16."},{"key":"e_1_2_9_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/JDT.2015.2501318"},{"key":"e_1_2_9_39_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.image.2017.11.001"},{"key":"e_1_2_9_40_2","doi-asserted-by":"crossref","unstructured":"Ronneberger Olaf Fischer Philipp andBrox Thomas. \u201cU-Net: Convolutional Networks for Biomedical Image Segmentation\u201d.Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015. Ed. by Navab Nassir Hornegger Joachim Wells William M. and Frangi Alejandro F. Cham: Springer International Publishing 2015 234\u2013241. isbn: 978-3-319-24574-4 4.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"e_1_2_9_41_2","doi-asserted-by":"publisher","DOI":"10.2312\/sr.20251183"},{"key":"e_1_2_9_42_2","doi-asserted-by":"publisher","DOI":"10.1145\/3652104.3652525"},{"key":"e_1_2_9_42_3","unstructured":"url:https:\/\/doi.org\/10.1145\/3652104.36525253 11."},{"key":"e_1_2_9_43_2","doi-asserted-by":"publisher","DOI":"10.1145\/1669112.1669135"},{"key":"e_1_2_9_43_3","unstructured":"url:https:\/\/doi.org\/10.1145\/1669112.16691352."},{"key":"e_1_2_9_44_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2007.06.006"},{"key":"e_1_2_9_45_2","doi-asserted-by":"publisher","DOI":"10.1145\/2493432.2493445"},{"key":"e_1_2_9_45_3","unstructured":"url:https:\/\/doi.org\/10.1145\/2493432.24934451."},{"key":"e_1_2_9_46_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"e_1_2_9_47_2","article-title":"Training deep neural networks with 8-bit floating point numbers","volume":"31","author":"Wang Naigang","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"e_1_2_9_48_2","doi-asserted-by":"publisher","DOI":"10.1145\/3264952"},{"key":"e_1_2_9_48_3","unstructured":"url:https:\/\/doi.org\/10.1145\/32649523."},{"key":"e_1_2_9_49_2","doi-asserted-by":"crossref","unstructured":"Wang Zhou Simoncelli Eero P andBovik Alan C.\u201cMultiscale structural similarity for image quality assessment\u201d.The Thrity-Seventh Asilomar Conference on Signals Systems & Computers 2003. Vol. 2. Ieee.2003 1398\u2013140215.","DOI":"10.1109\/ACSSC.2003.1292216"},{"key":"e_1_2_9_50_2","doi-asserted-by":"publisher","DOI":"10.1145\/3177102.3177121"},{"key":"e_1_2_9_50_3","unstructured":"url:https:\/\/doi.org\/10.1145\/3177102.31771213."},{"key":"e_1_2_9_51_2","unstructured":"Zhang Richard Isola Phillip Efros Alexei A et al. \u201cThe Unreasonable Effectiveness of Deep Features as a Perceptual Metric\u201d.CVPR.201815."}],"container-title":["Computer Graphics Forum"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/cgf.70369","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1111\/cgf.70369","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/cgf.70369","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T12:54:19Z","timestamp":1774875259000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1111\/cgf.70369"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,30]]},"references-count":65,"alternative-id":["10.1111\/cgf.70369"],"URL":"https:\/\/doi.org\/10.1111\/cgf.70369","archive":["Portico"],"relation":{},"ISSN":["0167-7055","1467-8659"],"issn-type":[{"value":"0167-7055","type":"print"},{"value":"1467-8659","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,30]]},"assertion":[{"value":"2026-03-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70369"}}