MI-GAN: A Simple Baseline for Image Inpainting on Mobile Devices

Andranik Sargsyan, Shant Navasardyan, Xingqian Xu, Humphrey Shi; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2023, pp. 7335-7345

In recent years, many deep learning based image inpainting methods have been developed by the research community. Some of those methods have shown impressive image completion abilities. Yet, to the best of our knowledge, there is no image inpainting model designed to run on mobile devices. In this paper we present a simple image inpainting baseline, Mobile Inpainting GAN (MI-GAN), which is approximately one order of magnitude computationally cheaper and smaller than existing state-of-the-art inpainting models, and can be efficiently deployed on mobile devices. Excessive quantitative and qualitative evaluations show that MI-GAN performs comparable or, in some cases, better than recent state-of-the-art approaches. Moreover, we perform a user study comparing MI-GAN results with results from several commercial mobile inpainting applications, which clearly shows the advantage of MI-GAN in comparison to existing apps. With the purpose of high quality and efficient inpainting, we utilize an effective combination of adversarial training, model re-parametrization, and knowledge distillation. Our models and code are publicly available at https://github.com/Picsart-AI-Research/MI-GAN.