Poster
in
Workshop: Deep Generative Model in Machine Learning: Theory, Principle and Efficacy
Trustworthy Image Super-Resolution via Generative Pseudoinverse
Andreas Floros · Seyed-Mohsen Moosavi-Dezfooli · Pier Dragotti
Keywords: [ normalizing flows ] [ Structured data modeling ] [ super-resolution ] [ diffusion models ]
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. Code will be released upon acceptance.