Abstract

Low-light image enhancement (LLIE) is the process of improving the quality of images taken in low-light conditions while striking a balance between enhancing image illumination and maintaining their natural appearance. This involves reducing noise, enhancing details, and correcting colors, all while avoiding unwanted artifacts such as halo effects or color distortions. We propose LIVENet, a novel deep neural network that jointly performs noise reduction on low-light images and enhances illumination and texture details. LIVENet has two stages: the image enhancement stage and the refinement stage. We propose a Latent Subspace Denoising Block (LSDB) that uses a low-rank representation of low-light features to suppress the noise and predict a noise-free grayscale image. We propose enhancing an RGB image by eliminating noise. This is done by converting it into YCbCr color space and then replacing the noisy luminance (Y) channel with the predicted noisefree grayscale image. LIVENet also predicts the transmission map and atmospheric light in the image enhancement stage. By feeding them to an atmospheric scattering model, LIVENet produces an enhanced image with rich color and illumination. In the refinement stage, we propose an enhancement approach where texture information from the grayscale image is incorporated into the improved image using a Spatial Feature Transform (SFT) layer. Experiments on different datasets demonstrate that LIVENet's enhanced images consistently outperform previous techniques across various quality metrics.