Low-Light Image Enhancement via Gradient Prior-Aided Network

Abstract

Low-light images have low brightness and low contrast, which bring huge obstacles to the intelligent video surveillance system. The enhancement of low-light images must simultaneously consider the interference of factors such as brightness, contrast, artifacts, and noise. To this end, in this study, we propose a gradient prior-aided low-light enhancement network (GPANet). The main idea is to improve the network's ability to extract edge features and remove unwanted noise by introducing first-order (i.e., Sobel Filter) and second-order gradient (i.e., Laplacian Filter) features. Unlike in previous methods, in the proposed study, we first extract the first-order and second-order gradient information of low-light images and concatenate them with low-light images for multi-view feature analysis in the multi-view fusion encoder (MFE). Then, we suggest the multi-branch topology module (MTM) to fuse and decompose the multi-view features. Finally, we reconstruct the multi-view features through multi-view decomposition decoders (MDDs, including three sub-decoders) to generate potentially normal-light images. The firstand second-order gradient decoders will provide the enhancement decoder with multi-scale gradient prior features. Furthermore, we suggest a residual network to speed up network convergence while ensuring stable enhancement performance. We conduct experiments on widely adopted datasets. The results demonstrate the advantages of our method compared to other methods from both qualitative and quantitative perspectives.

Double Domain Guided Real-Time Low-Light Image Enhancement for Ultra-High-Definition Transportation Surveillance

“…Besides, in transportation scenes, edge feature restoration is typically important, which was rarely considered. Lu et al [49] proposed a gradient prior-aided neural network employing Laplacian and Sobel filters to guide the enhancement. However, these filters are sensitive to noise interference, which is harmful to image quality enhancement.…”

Non-Reference Enhanced Low-Light Image Estimation Using Zero-DCE with Filtering Refinement.

“…Striking a balance between computational efficiency and robust performance is crucial, particularly for real time applications [38]. There's a pressing need for the deep models that offer swift inference speeds and lower computational costs, especially for devices with limited resources, like mobile platforms, aiming for practical functionality [39]. This paper introduces a novel deep learning-based method, a modified version of the Zero-Reference Deep Curve Estimation (Zero-DCE), tailored for enhancing dark images [1].…”

“…Mainly, after this step, our approach incorporates a filtering process applied to enhanced image [47]. This filtering process further refines the image, aiming to augment its quality by decreasing the noise that might have emerged during enhancement process [39]. A pivotal aspect of our approach is its differentiability, allowing learning of adjustable curve parameters through a convolutional neural network [28].…”