首站-论文投稿智能助手
典型文献
End-to-end learning of 3D phase-only holograms for holographic display
文献摘要:
Computer-generated holography(CGH)provides volumetric control of coherent wavefront and is fundamental to applications such as volumetric 3D displays,lithography,neural photostimulation,and optical/acoustic trapping.Recently,deep learning-based methods emerged as promising computational paradigms for CGH synthesis that overcome the quality-runtime tradeoff in conventional simulation/optimization-based methods.Yet,the quality of the predicted hologram is intrinsically bounded by the dataset's quality.Here we introduce a new hologram dataset,MIT-CGH-4K-V2,that uses a layered depth image as a data-efficient volumetric 3D input and a two-stage supervised+unsupervised training protocol for direct synthesis of high-quality 3D phase-only holograms.The proposed system also corrects vision aberration,allowing customization for end-users.We experimentally show photorealistic 3D holographic projections and discuss relevant spatial light modulator calibration procedures.Our method runs in real-time on a consumer GPU and 5 FPS on an iPhone 13 Pro,promising drastically enhanced performance for the applications above.
文献关键词:
作者姓名:
Liang Shi;Beichen Li;Wojciech Matusik
作者机构:
Computer Science and Artificial Intelligence Laboratory,Massachusetts Institute of Technology,32 Vassar St,Cambridge,MA 02139,USA
引用格式:
[1]Liang Shi;Beichen Li;Wojciech Matusik-.End-to-end learning of 3D phase-only holograms for holographic display)[J].光:科学与应用(英文版),2022(09):2176-2193
A类:
photostimulation,supervised+unsupervised
B类:
End,end,learning,phase,only,holograms,holographic,Computer,generated,holography,CGH,provides,volumetric,control,coherent,wavefront,fundamental,applications,such,displays,lithography,neural,optical,acoustic,trapping,Recently,deep,methods,emerged,promising,computational,paradigms,synthesis,that,overcome,quality,runtime,tradeoff,conventional,simulation,optimization,Yet,predicted,intrinsically,bounded,by,dataset,Here,we,introduce,new,MIT,4K,V2,uses,layered,depth,image,efficient,input,two,stage,training,protocol,direct,high,proposed,system,also,corrects,vision,aberration,allowing,customization,users,We,experimentally,show,photorealistic,projections,discuss,relevant,spatial,light,modulator,calibration,procedures,Our,runs,consumer,GPU,FPS,iPhone,Pro,drastically,enhanced,performance,above
AB值:
0.674361
相似文献
Harvesting random embedding for high-frequency change-point detection in temporal complex systems
Jia-Wen Hou;Huan-Fei Ma;Dake He;Jie Sun;Qing Nie;Wei Lin-Research Institute of Intelligent Complex Systems,Fudan University,Shanghai 200433,China;Centre for Computational Systems Biology,Institute of Science and Technology for Brain-Inspired Intelligence,Fudan University,Shanghai 200433,China;School of Mathematical Sciences,Soochow University,Suzhou 215006,China;Xinhua Hospital Affiliated to Shanghai Jiao Tong University School of Medicine,Shanghai 200092,China;School of Mathematical Sciences and Shanghai Center for Mathematical Sciences,Fudan University,Shanghai 200433,China;Department of Mathematics,Department of Developmental and Cell Biology,and NSF-Simons Center for Multiscale Cell Fate Research,University of California,Irvine,CA 92697-3875,USA;Shanghai Key Laboratory for Contemporary Applied Mathematics,LNMS(Fudan University),and LCNBI(Fudan University),Shanghai 200433,China;State Key Laboratory of Medical Neurobiology,and MOE Frontiers Center for Brain Science,Institutes of Brain Science,Fudan University,Shanghai 200032,China
机标中图分类号,由域田数据科技根据网络公开资料自动分析生成,仅供学习研究参考。