Generative Adversarial Optical Networks Using Diffractive Layers for Digit and Action Generation

Within the traditional electronic neural network framework, Generative Adversarial Networks (GANs) have achieved extensive applications across multiple domains, including image synthesis, style transfer and data augmentation. Recently, several studies have explored the use of optical neural networks represented by the diffractive deep neural network (D2NN) for GANs. However, most of these focus on applications of the generative network, and there is currently no well-established D2NN architecture that simultaneously implements generative adversarial functionality. Here, we propose a novel implementation scheme for generative adversarial networks based on all-optical diffraction layers, demonstrating a complete all-optical adversarial architecture that simultaneously realizes both the generative network and the adversarial network (D2NN-GAN). We validated this method on the MNIST handwritten digit dataset, achieving Nash equilibrium convergence with the discriminator accuracy stabilizing around 50%. Concurrently, the average SSIM parameter of generated images reached 0.9573, indicating that the generated samples possess high quality and closely resemble real samples. Furthermore, we extended the framework to the KTH human action dataset, successfully reconstructing the “running” action with a discriminator accuracy of approximately 75%. The D2NN-GAN architecture introduces a fully optical generative adversarial model, providing a practical path for future optical modeling methods, such as image generation and video synthesis.