Trustworthy Image Super-Resolution via Generative Pseudoinverse

Andreas Floros, Seyed-Mohsen Moosavi-Dezfooli, Pier Luigi Dragotti

Track: tiny / short paper (up to 4 pages)

Keywords: Super-resolution, diffusion models, normalizing flows

TL;DR: We develop generative super-resolution models that maintain high quality while ensuring asymptotic consistency with low-resolution measurements.

Abstract: We consider the problem of trustworthy image restoration, taking the form of a constrained optimization over the prior density. To this end, we develop generative models for the task of image super-resolution that respect the degradation process and that can be made asymptotically consistent with the low-resolution measurements, outperforming existing methods by a large margin in that respect.

Submission Number: 68