arrow
Return

Realistic blur layer-based computer-generated holography

delete2025-06-06
delete0
PRE
AI
Z
Zichun Le *
A
Aoxin Fei
X
X.R. Duan
S
Shun Li
DOI:10.1016/j.optlaseng.2025.109081delete
deleteOriginal
deleteOriginal request for help
deleteShare
deleteSave
Abstract

Abstract

En 中文
Computer Generated Holography (CGH) based on deep learning has rapidly advanced, surpassing traditional physics-based methods that rely on optical wave simulations and signal processing. We propose a multilayer hologram generation model for generating 3D Phase-only holograms (POHs) using a layer-based approach. The 3D object is represented as multiple layers, with Gaussian convolution kernels applied to generate target images that simulate realistic blur effects for non-focal layers. The model utilizes learnable initial phases to train and optimize the blur effects across these layers. By taking amplitude and depth images as input, the proposed method is capable of synthesizing both 2D and 3D holograms with realistic blur effects. Both simulations and optical experiments demonstrate that the proposed method achieves exceptional hologram generation performance, with blur effects closely matching those observed in real-world scenarios.
Keywords:
Computer generated holography
Deep learning
Realistic blur
Layer-based methods
Non-focal layers

Journal

Optics and Lasers in Engineering cover
Optics and Lasers in Engineering
IF:
3.7
Papers:
7.3K
Citations:
1.7W

Organization

Z
Zhejiang Univ Technol
Scholars:
2.7K
Papers: 978
Citations: 382
Cited Papers

Cited Papers

Multi-depth hologram generation using stochastic gradient descent algorithm with complex loss function
err2021-04-30
err75
errOAAI
errChen, Chun; Lee, Byounghyo; Li, Nan-Nan; Chae, Minseok; Wang, Di; Wang, Qiong-Hua; Lee, Byoungho
errShare
errSave
Neural Holography with Camera-in-the-loop Training
err2020-11-27
err232
PREAI
errPeng, Yifan; Choi, Suyeon; Padmanaban, Nitish; Wetzstein, Gordon
errShare
errSave
High-speed full analytical holographic computations for true-life scenes
err2010-02-02
err77
errOAAI
errLiu, Yuan-Zhi; Dong, Jian-Wen; Pu, Yi-Ying; Chen, Bing-Chu; He, He-Xiang; Wang, He-Zhou
errShare
errSave
Complex spatial light modulation capability of a dual layer in-plane switching liquid crystal panel
err2022-05-18
err11
errOAAI
errJang, Seong-Woo; Choi, Wonwoo; Kim, Soobin; Lee, Jonghyun; Na, Sehwan; Ham, Sangwon; Park, Juseong; Kang, Hoon; Ju, Byeong-Kwon; Kim, Hwi
errShare
errSave
High-speed computer-generated holography using an autoencoder-based deep neural network
err2021-06-14
err162
PREAI
errWu, Jiachen; Liu, Kexuan; Sui, Xiaomeng; Cao, Liangcai
errShare
errSave
Diffraction model-informed neural network for unsupervised layer-based computer-generated holography
err2022-11-23
err34
errOAAI
errShui, Xinghua; Zheng, Huadong; Xia, Inxing; Yang, Furong; Wang, Weisen; Yu, Yingjie
errShare
errSave
Towards real-time photorealistic 3D holography with deep neural networks
err2021-03-10
err0
errOAAI
errLiang Shi; Beichen Li; Changil Kim; Petr Kellnhofer; Wojciech Matusik
errShare
errSave
Real-time 4K computer-generated hologram based on encoding conventional neural network with learned layered phase
err2023-11-08
err7
errOAAI
errZhong, Chongli; Sang, Xinzhu; Yan, Binbin; Li, Hui; Xie, Xinhui; Qin, Xiujuan; Chen, Shuo
errShare
errSave
researcher View more