Denoising diffusion post-processing for low-light image enhancement

Loading...
Thumbnail Image

Authors

Panagiotou, Savvas
Bosman, Anna

Journal Title

Journal ISSN

Volume Title

Publisher

Elsevier

Abstract

Low-light image enhancement (LLIE) techniques attempt to increase the visibility of images captured in low-light scenarios. However, as a result of enhancement, a variety of image degradations such as noise and color bias are revealed. Furthermore, each particular LLIE approach may introduce a different form of flaw within its enhanced results. To combat these image degradations, post-processing denoisers have widely been used, which often yield oversmoothed results lacking detail. We propose using a diffusion model as a post-processing approach, and we introduce Low-light Post-processing Diffusion Model (LPDM) in order to model the conditional distribution between under-exposed and normally-exposed images. We apply LPDM in a manner which avoids the computationally expensive generative reverse process of typical diffusion models, and post-process images in one pass through LPDM. Extensive experiments demonstrate that our approach outperforms competing post-processing denoisers by increasing the perceptual quality of enhanced low-light images on a variety of challenging low-light datasets. Source code is available at https://github.com/savvaki/LPDM.

Description

DATA AVAILABILITY : The public link to the code is specified in the manuscript. The datasets are listed in the manuscript and are open source/widely available.

Keywords

Low-light image enhancement (LLIE), Diffusion model, Denoising, Post-processing, SDG-09: Industry, innovation and infrastructure, Low-light post-processing diffusion model (LPDM)

Sustainable Development Goals

SDG-09: Industry, innovation and infrastructure

Citation

Panagiotou, S. & Bosman, A.S. 2024, 'Denoising diffusion post-processing for low-light image enhancement', Pattern Recognition, vol. 156, art. 110799, pp. 1-13, doi : 10.1016/j.patcog.2024.110799.