RELD: Regularization by Latent Diffusion Models for Image Restoration

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Cascarano, Pasquale, Stacchio, Lorenzo, Sebastiani, Andrea, Benfenati, Alessandro, Kamilov, Ulugbek S., Marfia, Gustavo
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912299522981888
author Cascarano, Pasquale
Stacchio, Lorenzo
Sebastiani, Andrea
Benfenati, Alessandro
Kamilov, Ulugbek S.
Marfia, Gustavo
author_facet Cascarano, Pasquale
Stacchio, Lorenzo
Sebastiani, Andrea
Benfenati, Alessandro
Kamilov, Ulugbek S.
Marfia, Gustavo
contents In recent years, Diffusion Models have become the new state-of-the-art in deep generative modeling, ending the long-time dominance of Generative Adversarial Networks. Inspired by the Regularization by Denoising principle, we introduce an approach that integrates a Latent Diffusion Model, trained for the denoising task, into a variational framework using Half-Quadratic Splitting, exploiting its regularization properties. This approach, under appropriate conditions that can be easily met in various imaging applications, allows for reduced computational cost while achieving high-quality results. The proposed strategy, called Regularization by Latent Denoising (RELD), is then tested on a dataset of natural images, for image denoising, deblurring, and super-resolution tasks. The numerical experiments show that RELD is competitive with other state-of-the-art methods, particularly achieving remarkable results when evaluated using perceptual quality metrics.
format Preprint
id arxiv_https___arxiv_org_abs_2503_22563
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle RELD: Regularization by Latent Diffusion Models for Image Restoration
Cascarano, Pasquale
Stacchio, Lorenzo
Sebastiani, Andrea
Benfenati, Alessandro
Kamilov, Ulugbek S.
Marfia, Gustavo
Image and Video Processing
Computer Vision and Pattern Recognition
In recent years, Diffusion Models have become the new state-of-the-art in deep generative modeling, ending the long-time dominance of Generative Adversarial Networks. Inspired by the Regularization by Denoising principle, we introduce an approach that integrates a Latent Diffusion Model, trained for the denoising task, into a variational framework using Half-Quadratic Splitting, exploiting its regularization properties. This approach, under appropriate conditions that can be easily met in various imaging applications, allows for reduced computational cost while achieving high-quality results. The proposed strategy, called Regularization by Latent Denoising (RELD), is then tested on a dataset of natural images, for image denoising, deblurring, and super-resolution tasks. The numerical experiments show that RELD is competitive with other state-of-the-art methods, particularly achieving remarkable results when evaluated using perceptual quality metrics.
title RELD: Regularization by Latent Diffusion Models for Image Restoration
topic Image and Video Processing
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2503.22563