计算机科学
人工智能
全息术
人工神经网络
卷积神经网络
初始化
过度拟合
图像质量
时域
计算机视觉
光学
图像(数学)
物理
程序设计语言
作者
Huadong Zheng,Junchang Peng,Zhen Wang,Xinghua Shui,Yingjie Yu,Xinxing Xia
出处
期刊:Optics Express
[The Optical Society]
日期:2023-05-30
卷期号:31 (12): 19931-19931
被引量:7
摘要
Learning-based computer-generated holography (CGH) has demonstrated great potential in enabling real-time, high-quality holographic displays. However, most existing learning-based algorithms still struggle to produce high-quality holograms, due to the difficulty of convolutional neural networks (CNNs) in learning cross-domain tasks. Here, we present a diffraction model-driven neural network (Res-Holo) using hybrid domain loss for phase-only hologram (POH) generation. Res-Holo utilizes the weights of the pretrained ResNet34 as the initialization during the encoder stage of the initial phase prediction network to extract more generic features and also to help prevent overfitting. Also, frequency domain loss is added to further constrain the information that the spatial domain loss is insensitive. The peak signal-to-noise ratio (PSNR) of the reconstructed image is improved by 6.05 dB using hybrid domain loss compared to using spatial domain loss alone. Simulation results show that the proposed Res-Holo can generate high-fidelity 2 K resolution POHs with an average PSNR of 32.88 dB at 0.014 seconds/frame on the DIV2K validation set. Both monochrome and full-color optical experiments show that the proposed method can effectively improve the quality of reproduced images and suppress image artifacts.
科研通智能强力驱动
Strongly Powered by AbleSci AI