Low-light image enhancement based on U-Net and Haar wavelet

This poster was published at the 29th International Conference on Multimedia Modeling, organized from the 9th until the 12th of January, 2023 in Bergen, Norway. 

Abstract

Low-light image enhancement has been very popular for improving the visual quality of image representations, while low-light images often require advanced techniques to improve the perception of information for a human viewer. One of the main objectives in increasing the lighting conditions is to retain patterns, texture, and style with minimal deviations from the considered image. To this direction, we propose a low-light image enhancement method with Haar wavelet-based pooling to preserve texture regions and increase their quality