Speckle-free holography with a diffraction-aware global perceptual model  

作　　者：YIRAN WEI YIYUN CHEN MI ZHOU MU KU CHEN SHUMING JIAO QINGHUA SONG XIAO-PING ZHANG ZIHAN GENG 

机构地区：[1]Tsinghua Shenzhen International Graduate School,Tsinghua University,Shenzhen 518055,China [2]Department of Electrical Engineering,City University of Hong Kong,Hong Kong 999077,China [3]Department of Engineering,Shenzhen MSU-BIT University,Shenzhen 518172,China

出　　处：《Photonics Research》2024年第11期2418-2423,共6页光子学研究(英文版)

基　　金：National Natural Science Foundation of China(62305184);Science,Technology and Innovation Commission of Shenzhen Municipality(WDZC20220818100259004);Basic and Applied Basic Research Foundation of Guangdong Province(2023A1515012932);The Research Grants Council of the Hong Kong Special Administrative Region,China(C5031-22G;City U11310522,City U11300123);Department of Science and Technology of Guangdong Province(2020B1515120073);City University of Hong Kong(9610628);Shenzhen Key Laboratory of Ubiquitous Data Enabling(ZDSYS20220527171406015);Tsinghua Shenzhen International Graduate School-Shenzhen Pengrui Endowed Professorship Scheme of Shenzhen Pengrui Foundation。

摘　　要：Computer-generated holography(CGH)based on neural networks has been actively investigated in recent years,and convolutional neural networks(CNNs)are frequently adopted.A convolutional kernel captures local dependencies between neighboring pixels.However,in CGH,each pixel on the hologram influences all the image pixels on the observation plane,thus requiring a network capable of learning long-distance dependencies.To tackle this problem,we propose a CGH model called Holomer.Its single-layer perceptual field is 43 times larger than that of a widely used 3×3 convolutional kernel,thanks to the embedding-based feature dimensionality reduction and multi-head sliding-window self-attention mechanisms.In addition,we propose a metric to measure the networks'learning ability of the inverse diffraction process.In the simulation,our method demonstrated noteworthy performance on the DIV2K dataset at a resolution of 1920×1024,achieving a PSNR and an SSIM of 35.59 d B and 0.93,respectively.The optical experiments reveal that our results have excellent image details and no observable background speckle noise.This work paves the path of high-quality hologram generation.

关 键 词：process CONVOLUTION KERNEL 

分 类 号：O43[机械工程—光学工程]