SUD^2: Supervision by Denoising Diffusion Models for Image Reconstruction
share
Many imaging inverse problemsx2014such as image-dependent in-painting and dehazingx2014are challenging because their forward models are unknown or depend on unknown latent parameters. While one can solve such problems by training a neural network with vast quantities of paired training data, such paired training data is often unavailable. In this paper, we propose a generalized framework for training image reconstruction networks when paired training data is scarce. In particular, we demonstrate the ability of image denoising algorithms and, by extension, denoising diffusion models to supervise network training in the absence of paired training data.
READ FULL TEXT