Yan Xingpeng, Li Jiaqi, Zhang Yanan, Chang Hebin, Hu Hairong, Jing Tao, Li Hanyu, Zhang Yang, Xue Jinhong, Yu Xunbo, Jiang Xiaoyu
Department of Information Communication, Army Academy of Armored Forces, Beijing, 100072, China.
School of Electronic Engineering, Beijing University of Posts and Telecommunications, Beijing, 100080, China.
Adv Sci (Weinh). 2025 Feb;12(8):e2408610. doi: 10.1002/advs.202408610. Epub 2024 Dec 31.
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.
通过基于学习的方法生成用于3D场景的计算机生成全息图（CGH），可以以更高的质量和更快的速度重建任意3D场景。然而，3D高分辨率数据集获取的同质化和困难严重限制了模型的泛化能力。提出了一种新颖的方法，使用2D图像数据集训练基于卷积神经网络（CNN）的3D编码模型。该技术产生具有统计均匀分布的虚拟深度（VD）图像。此方法采用通过角谱方法（ASM）训练的CNN逐层计算衍射场。一种用于纯相位编码的全卷积神经网络架构，在DIV2K-VD数据集上进行训练。实验结果通过仅在0.061秒内生成4K纯相位全息图验证了其有效性，产生的高质量全息图平均PSNR为34.7 dB，SSIM为0.836，与传统方法相比具有高质量、经济性和时间效率。
