IVCVMar 16, 2023

Denoising Diffusion Post-Processing for Low-Light Image Enhancement

arXiv:2303.09627v244 citationsh-index: 15Has Code
AI Analysis

This addresses image quality issues for users of low-light photography, but it is incremental as it builds on existing diffusion models for a specific application.

The paper tackles the problem of image degradations like noise and color bias in low-light image enhancement by proposing a diffusion model for post-processing, which outperforms competing denoisers by improving perceptual quality on challenging datasets.

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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes