DiffGANPaint: Fast Inpainting Using Denoising Diffusion GANs

Moein Heidari, Alireza Morsali, Tohid Abedini, Samin Heydarian

Keywords: Inpainting, GAN, Denosing Diffusion

TL;DR: Leverage the benefits of a novel denoising diffusion probabilistic model and GAN model solution for the image inpainting task

Abstract: Free-form image inpainting is the task of reconstructing parts of an image specified by an arbitrary binary mask. In this task, it is typically desired to generalize model capabilities to unseen mask types, rather than learning certain mask distributions. Capitalizing on the advances in diffusion models, in this paper, we propose a Denoising Diffusion Probabilistic Model (DDPM) based model capable of filling missing pixels fast as it models the backward diffusion process using the generator of a generative adversarial network (GAN) network to reduce sampling cost in diffusion models. Experiments on general-purpose image inpainting datasets verify that our approach performs superior or on par with most contemporary works.