From picture to 3D hologram: end-to-end learning of real-time 3D photorealistic hologram generation from 2D image input

被引：11

作者：

Chang, Chenliang ^{[1
,2
,3
]}

Dai, Bo ^{[1
,2
]}

Zhu, Dongchen

LI, Jiamao ^{[3
]}

Xia, Jun ^{[4
]}

Zhang, Dawei ^{[1
,2
]}

Hou, Lianping ^{[5
]}

Zhuang, Songlin ^{[1
,2
]}

机构：

[1] Univ Shanghai Sci & Technol, Engn Res Ctr Opt Instrument & Syst, Sch Opt Elect & Comp Engn, Minist Educ, Shanghai 200093, Peoples R China

[2] Univ Shanghai Sci & Technol, Shanghai Key Lab Modern Opt Syst, Shanghai 200093, Peoples R China

[3] Chinese Acad Sci, Shanghai Inst Microsyst & Informat Technol, Bion Vis Syst Lab, State Key Lab Transducer Technol, Shanghai 200050, Peoples R China

[4] Southeast Univ, Sch Elect Sci & Engn, Joint Int Res Lab Informat Display & Visualizat, Nanjing 210096, Peoples R China

[5] Univ Glasgow, James Watt Sch Engn, Glasgow G12 8QQ, Scotland

来源：

OPTICS LETTERS | 2023年 / 48卷 / 04期

基金：

中国国家自然科学基金;

关键词：

DISPLAY;

D O I：

10.1364/OL.478976

中图分类号：

O43 [光学];

学科分类号：

070207 ; 0803 ;

摘要：

In this Letter, we demonstrate a deep-learning-based method capable of synthesizing a photorealistic 3D hologram in real-time directly from the input of a single 2D image. We design a fully automatic pipeline to create large-scale datasets by converting any collection of real-life images into pairs of 2D images and corresponding 3D holograms and train our convolutional neural network (CNN) end-to-end in a supervised way. Our method is extremely computation -efficient and memory-efficient for 3D hologram generation merely from the knowledge of on-hand 2D image content. We experimentally demonstrate speckle-free and photoreal-istic holographic 3D displays from a variety of scene images, opening up a way of creating real-time 3D holography from everyday pictures. (c) 2023 Optical Society of America (c) 2023 Optica Publishing Group

引用

页码：851 / 854

页数：4