近日，韩国汉阳大学Park, Won Il团队研究了图像处理与光学矩阵矢量乘法器实现的编码和解码任务。相关论文于2025年7月22日发表在《光：科学与应用》杂志上。

研究组介绍了一种基于光学神经网络（ONN）的自动编码器，用于有效的图像处理，利用专门的光学矩阵矢量乘法器进行编码和解码任务。为了解决高效解码的挑战，他们提出了一种通过标量乘法优化输出处理的方法，提高了生成高维输出的性能。通过采用系统上的迭代调谐，研究组减轻了硬件缺陷和噪声，逐步提高图像重建精度到接近数字质量。

此外，该方法支持降噪和光学图像生成，支持去噪自编码器、变分自编码器和生成对抗网络等模型。该研究结果表明，基于ONN的系统有潜力超越传统电子系统的能源效率，在医疗成像、自动驾驶汽车和边缘计算等应用中实现实时、低功耗的图像处理。

附：英文原文

Title: Image processing with Optical matrix vector multipliers implemented for encoding and decoding tasks

Author: Kim, Minjoo, Kim, Yelim, Park, Won Il

Issue&Volume: 2025-07-22

Abstract: This study introduces an optical neural network (ONN)-based autoencoder for efficient image processing, utilizing specialized optical matrix-vector multipliers for both encoding and decoding tasks. To address the challenges in efficient decoding, we propose a method that optimizes output processing through scalar multiplications, enhancing performance in generating higher-dimensional outputs. By employing on-system iterative tuning, we mitigate hardware imperfections and noise, progressively improving image reconstruction accuracy to near-digital quality. Furthermore, our approach supports noise reduction and optical image generation, enabling models such as denoising autoencoders, variational autoencoders, and generative adversarial networks. Our results demonstrate that ONN-based systems have the potential to surpass the energy efficiency of traditional electronic systems, enabling real-time, low-power image processing in applications such as medical imaging, autonomous vehicles, and edge computing.

DOI: 10.1038/s41377-025-01904-z

Source: https://www.nature.com/articles/s41377-025-01904-z