典型文献
Machine-learning-based high-speed lensless large-field holographic projection using double-sampling Fresnel diffraction method
文献摘要：
Machine learning can effectively accelerate the runtime of a computer-generated hologram.However,the angular spec-trum method and single fast Fresnel transform-based machine learning acceleration algorithms are still limited in the field-of-view angle of projection.In this paper,we propose an efficient method for the fast generation of large field-of-view holograms combining stochastic gradient descent[SGD],neural networks,and double-sampling Fresnel diffraction[DSFD].Compared with the traditional Gerchberg-Saxton[GS]algorithm,the DSFD-SGD algorithm has better reconstruction quality.Our neural network can be automatically trained in an unsupervised manner with a training set of target images without labels,and its combination with the DSFD can improve the optimization speed significantly.The proposed DSFD-Net method can generate 2000-resolution holograms in 0.05 s.The feasibility of the proposed method is demonstrated with simulations and experiments.
文献关键词：
中图分类号：
作者姓名：
Chentianfei Shen;Tong Shen;Qi Chen;Qinghan Zhang;Jihong Zheng
作者机构：
School of Optical-Electrical and Computer Engineering,University of Shanghai for Science and Technology,Shanghai 200433,China
文献出处：
引用格式：
[1]Chentianfei Shen;Tong Shen;Qi Chen;Qinghan Zhang;Jihong Zheng-.Machine-learning-based high-speed lensless large-field holographic projection using double-sampling Fresnel diffraction method)[J].中国光学快报（英文版）,2022(05):1-6
A类：
DSFD
B类：
Machine,learning,high,speed,lensless,large,field,holographic,projection,using,double,sampling,Fresnel,diffraction,method,effectively,accelerate,runtime,computer,generated,However,angular,spec,trum,single,fast,transform,machine,acceleration,algorithms,still,limited,view,angle,In,this,paper,efficient,generation,holograms,combining,stochastic,gradient,descent,SGD,neural,networks,Compared,traditional,Gerchberg,Saxton,GS,better,reconstruction,quality,Our,automatically,trained,unsupervised,manner,training,set,target,images,without,labels,its,combination,improve,optimization,significantly,proposed,Net,resolution,feasibility,demonstrated,simulations,experiments
AB值：
0.568773
相似文献
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。
