Trustworthy Image Super-Resolution via Generative Pseudoinverse

TL;DR

This paper introduces a new generative model-based approach for trustworthy image super-resolution that respects the degradation process and ensures consistency with low-resolution measurements, significantly improving reliability.

Contribution

It proposes a novel generative pseudoinverse method for image super-resolution that guarantees asymptotic consistency with measurements, enhancing trustworthiness.

Findings

Outperforms existing super-resolution methods in measurement consistency

Ensures asymptotic consistency with low-resolution data

Provides a reliable framework for trustworthy image restoration

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.