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

Chang, C., Dai, B., Zhu, D., Li, J., Xia, J., Zhang, D., Hou, L. and Zhuang, S. (2023) From picture to 3D holography: end-to-end learning of real-time 3D photorealistic hologram generation from 2D image input. Optics Letters, 48(4), pp. 851-854. (doi: 10.1364/OL.478976)

Abstract

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 photorealistic holographic 3D displays from a variety of scene images, opening up a way of creating real-time 3D holography from everyday pictures. © 2023 Optical Society of America

• Item Type: Articles
• Status: Published
• Refereed: Yes
• Glasgow Author(s) Enlighten ID: Hou, Dr Lianping and Zhang, Professor Dawei
• Authors: Chang, C., Dai, B., Zhu, D., Li, J., Xia, J., Zhang, D., Hou, L., and Zhuang, S.
• College/School: College of Science and Engineering > School of Engineering; College of Science and Engineering > School of Engineering > Electronics and Nanoscale Engineering
• Journal Name: Optics Letters
• Publisher: Optical Society of America
• ISSN: 0146-9592
• ISSN (Online): 1539-4794
• Copyright Holders: Copyright © 2023 Optical Society of America
• First Published: First published in Optics Letters 48(4):851-854
• Publisher Policy: Reproduced in accordance with the copyright policy of the publisher