Denoising in Mode Conversion by Utilizing Diffractive Deep Neural Networks Optimized With Reinforcement Learning (W2B.13)
Presenter: Zheng Li, Tianjin University
We propose a reinforcement-learning-optimized nonlinear physical diffractive neural network, which can simultaneously perform OAM-mode and LP-mode conversion with Gaussian noise removal. The PSNR and SSIM of the converted modes reach 27.94 dB and 0.838, respectively.
Authors:Zheng Li, Tianjin University / Wenbo Zhang, Tianjin University / Yang Wang, Tianjin University / Guanju Peng, Tianjin University / Zongze Li, Peng Cheng Laboratory / Xiaoyan Zhou, Tianjin University / Lin Zhang, Tianjin University