Panagiotou, SavvasBosman, Anna2024-08-262024-08-262024-12Panagiotou, 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.2024.110799.0031-3203 (print)1873-5142 (online)10.1016/j.patcog.2024.110799http://hdl.handle.net/2263/97851DATA 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.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.en© 2024 The Authors. Published by Elsevier Ltd. This is an open access article under the CC BY-NC license.Low-light image enhancement (LLIE)Diffusion modelDenoisingPost-processingSDG-09: Industry, innovation and infrastructureLow-light post-processing diffusion model (LPDM)Article