SCB-GAN: A High-Quality Small Celestial Body Surface Image Synthesis Method

Small celestial body (SCB) exploration is a research hot spot in deep space exploration technology. However, the scarcity of SCB surface images severely hinders the development of probe intelligence systems, and it is challenging to redeploy probes to obtain massive images due to the high cost. In recent years, with the growth of deep learning, generative adversarial networks (GANs) have shown excellent potential in generating real images. This article presents a high-quality SCB surface image synthesis method, SCB-GAN, which can generate a massive amount and a large diversity of SCB surface images that match human perception from a limited dataset. Specifically, we propose MineAug, which can automatically select appropriate data augmentations from the given SCB surface imageset based on an efficient mining mechanism, improving the robustness of the GAN training process. We also added vision-aided loss to our network to further improve image quality. Through extensive experiments, our method outperforms recent methods under a variety of metrics in terms of visual quality comparison, no-referenced image quality assessment, and human subjective evaluation, which has significant implications for the development of intelligent systems.