4K-DMDNet:diffraction model-driven network for 4K computer-generated holography

作     者：Kexuan Liu Jiachen Wu Zehao He Liangcai Cao Kexuan Liu;Jiachen Wu;Zehao He;Liangcai Cao

作者机构：State Key Laboratory of Precision Measurement Technology and InstrumentsDepartment of Precision InstrumentsTsinghua UniversityBeijing 100084China 

出 版 物：《Opto-Electronic Advances》 (光电进展（英文）)

年 卷 期：2023年第6卷第5期

页      面：17-29页

核心收录：

学科分类：070207[理学-光学] 07[理学] 08[工学] 080203[工学-机械设计及理论] 0802[工学-机械工程] 0803[工学-光学工程] 0702[理学-物理学] 

基　　金：We are grateful for financial supports from National Natural Science Foundation of China(62035003,61775117) China Postdoctoral Science Foundation(BX2021140) Tsinghua University Initiative Scientific Research Program(20193080075) 

主　　题：computer-generated holography deep learning model-driven neural network sub-pixel convolution oversampling 

摘      要：Deep learning offers a novel opportunity to achieve both high-quality and high-speed computer-generated holography(CGH).Current data-driven deep learning algorithms face the challenge that the labeled training datasets limit the training performance and *** model-driven deep learning introduces the diffraction model into the neural *** eliminates the need for the labeled training dataset and has been extensively applied to hologram ***,the existing model-driven deep learning algorithms face the problem of insufficient *** this study,we propose a model-driven neural network capable of high-fidelity 4K computer-generated hologram generation,called 4K Diffraction Model-driven Network(4K-DMDNet).The constraint of the reconstructed images in the frequency domain is *** a network structure that combines the residual method and sub-pixel convolution method is built,which effectively enhances the fitting ability of the network for inverse *** generalization of the 4K-DMDNet is demonstrated with binary,grayscale and 3D ***-quality full-color optical reconstructions of the 4K holograms have been achieved at the wavelengths of 450 nm,520 nm,and 638 nm.