Generation of Multiple‐Depth 3D Computer‐Generated Holograms from 2D‐Image‐Datasets Trained CNN
Xingpeng Yan, Jiaqi Li, Yanan Zhang, Hebin Chang, Hairong Hu, Tao Jing, Hanyu Li, Yang Zhang, Jinhong Xue, Xunbo Yu, Xiaoyu Jiang
Abstract
Generating computer-generated holograms (CGHs) for 3D scenes by learning-based methods can reconstruct arbitrary 3D scenes with higher quality and faster speed. However, the homogenization and difficulty of obtaining 3D high-resolution datasets seriously limit the generalization ability of the model. A novel approach is proposed to train 3D encoding models based on convolutional neural networks (CNNs) using 2D image datasets. This technique produces virtual depth (VD) images with a statistically uniform distribution. This approach employs a CNN trained with the angular spectrum method (ASM) for calculating diffraction fields layer by layer. A fully convolutional neural network architecture for phase-only encoding, which is trained on the DIV2K-VD dataset. Experimental results validate its effectiveness by generating a 4K phase-only hologram within only 0.061 s, yielding high-quality holograms that have an average PSNR of 34.7 dB along with an SSIM of 0.836, offering high quality, economic and time efficiencies compared to traditional methods.