Trustworthy Image Super-Resolution via Generative Pseudoinverse

Andreas Floros, Seyed-Mohsen Moosavi-Dezfooli, Pier Luigi Dragotti
5/18/2025
eess.IVcs.LG

No official code found. Best implementation: andreasfloros/trustworthy-super-resolution (3 stars, MIT, last commit 2025-07-21).

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.

View on arXivView PDF

Code Implementations(1)

andreasfloros/trustworthy-super-resolutionCommunity100%
MIT

Trustworthy Image Super-Resolution via Generative Pseudoinverse [ICLR 2025 DeLTa Workshop]

30PythonMar 9, 20251 years agoMIT
diffusion-modelnormalizing-flowsuper-resolution

Similar Papers

Image Super-Resolution with Guarantees via Conformalized Generative Models

85% match1 repo22025

Evaluating and Preserving High-level Fidelity in Super-Resolution

83% match2025

Robust Unsupervised StyleGAN Image Restoration

82% match2026

ControlSR: Taming Diffusion Models for Consistent Real-World Image Super Resolution

82% match1 repo132024

FaithDiff: Unleashing Diffusion Priors for Faithful Image Super-resolution

80% match2026

SeeSR: Towards Semantics-Aware Real-World Image Super-Resolution

80% match1 repo6582026

Cite this paper

@article{floros2025trustworthy,
  title  = {Trustworthy Image Super-Resolution via Generative Pseudoinverse},
  author = {Andreas Floros and Seyed-Mohsen Moosavi-Dezfooli and Pier Luigi Dragotti},
  year   = {2025},
  eprint = {2505.12375},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2505.12375v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2505.12375.svg)](https://codeofpaper.com/paper/2505.12375)

Discussion