Trustworthy Image Super-Resolution via Generative Pseudoinverse

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.

Cite

Text

Floros et al. "Trustworthy Image Super-Resolution via Generative Pseudoinverse." ICLR 2025 Workshops: DeLTa, 2025.

Markdown

[Floros et al. "Trustworthy Image Super-Resolution via Generative Pseudoinverse." ICLR 2025 Workshops: DeLTa, 2025.](https://mlanthology.org/iclrw/2025/floros2025iclrw-trustworthy/)

BibTeX

@inproceedings{floros2025iclrw-trustworthy,
  title     = {{Trustworthy Image Super-Resolution via Generative Pseudoinverse}},
  author    = {Floros, Andreas and Moosavi-Dezfooli, Seyed-Mohsen and Dragotti, Pier Luigi},
  booktitle = {ICLR 2025 Workshops: DeLTa},
  year      = {2025},
  url       = {https://mlanthology.org/iclrw/2025/floros2025iclrw-trustworthy/}
}