Optoelectronic generative adversarial networks

TL;DR

This paper introduces an optoelectronic generative adversarial network that combines optical and electronic computing to achieve high-speed, low-power generative AI tasks like image creation and restoration.

Contribution

It presents a novel hybrid optoelectronic GAN architecture that leverages transfer learning and integrates optical and electronic components for improved generative performance.

Findings

Demonstrated high-speed image generation and restoration

Achieved efficient training and inference with low power consumption

Validated superior performance across multiple generative tasks

Abstract

Artificial intelligence generative content technology has experienced remarkable breakthroughs in recent years and is quietly leading a profound transformation. Diffractive optical networks provide a promising solution for implementing generative model with high-speed and low-power consumption. In this work, we present the implementation of a generative model on the optoelectronic computing architecture, based on generative adversarial network, which is called optoelectronic generative adversarial network. The network strategically distributes the generator and discriminator across the optical and electronic components, which are seamlessly integrated to leverage the unique strengths of each computing paradigm and take advantage of transfer learning. The network can efficiently and high-speed process the complex tasks involved in the training and inference of the generative model. The superior performance of these networks is verified by engaging three types of generative tasks, image generation, conditional generation, and image restoration. By synergistically combining the strengths of optical and electronic computing, the optoelectronic generative adversarial network paves the way for the development of more powerful and accessible artificial intelligence generative content technology that can unlock new creative possibilities across a wide range of applications.