Deep generative models, such as diffusion models, GANs, and IMLE, have shown impressive capability in tackling inverse problems. However, the validity of model-generated solutions w.r.t. the forward problem and the reliability of associated uncertainty estimates remain understudied. This study evaluates recent diffusion-based, GAN-based, and IMLE-based methods on three inverse problems, i.e., 16× super-resolution, colourization, and image decompression. We assess the validity of these models' outputs as solutions to the inverse problems and conduct a thorough analysis of the reliability of the models' estimates of uncertainty over the solution. Overall, we find that the IMLE-based CHIMLE method outperforms other methods in terms of producing valid solutions and reliable uncertainty estimates.
@article{arxiv.2312.12691,
title = {How Good Are Deep Generative Models for Solving Inverse Problems?},
author = {Shichong Peng and Alireza Moazeni and Ke Li},
journal= {arXiv preprint arXiv:2312.12691},
year = {2023}
}