Trustworthy Image Super-Resolution via Generative Pseudoinverse

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Floros, Andreas, Moosavi-Dezfooli, Seyed-Mohsen, Dragotti, Pier Luigi
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908369269293056
author Floros, Andreas
Moosavi-Dezfooli, Seyed-Mohsen
Dragotti, Pier Luigi
author_facet Floros, Andreas
Moosavi-Dezfooli, Seyed-Mohsen
Dragotti, Pier Luigi
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2505_12375
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Trustworthy Image Super-Resolution via Generative Pseudoinverse
Floros, Andreas
Moosavi-Dezfooli, Seyed-Mohsen
Dragotti, Pier Luigi
Image and Video Processing
Machine Learning
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.
title Trustworthy Image Super-Resolution via Generative Pseudoinverse
topic Image and Video Processing
Machine Learning
url https://arxiv.org/abs/2505.12375