Abstract
Low-light image enhancement has been gradually becoming a hot research topic in recent years due to its wide usage as an important pre-processing step in computer vision tasks. Although numerous methods have achieved promising results, some of them still generate results with detail loss and local distortion. In this paper, we propose an improved generative adversarial network based on contextual information. Specifically, residual dense blocks are adopted in the generator to promote hierarchical feature interaction across multiple layers and enhance features at multiple depths in the network. Then, an attention module integrating multi-scale contextual information is introduced to refine and highlight discriminative features. A hybrid loss function containing perceptual and color component is utilized in the training phase to ensure the overall visual quality. Qualitative and quantitative experimental results on several benchmark datasets demonstrate that our model achieves relatively good results and has good generalization capacity compared to other state-of-the-art low-light enhancement algorithms.
Highlights
Nowadays, in a world where multimedia equipment is much more accessible, images and videos have become the most ubiquitous ways to convey and record information
We propose an improved generative adversarial network (GAN) for low-light image enhancement
Constructed an unsupervised GAN framework to perform low-light image enhancement without paired training samples. They used self-regularized attention mechanism and double discriminators, i.e., local and global discriminators, to handle the unevenly distributed lighting in the input image. All these works proved that GAN has great potential in low level image processing, and encoder–decoder structure in the generator plays a pivotal role for feature representation
Summary
In a world where multimedia equipment is much more accessible, images and videos have become the most ubiquitous ways to convey and record information. Some of them [1,2,3,4] adopted global histogram of input image to estimate the pixel transformation function, but they ignored the unevenly distributed darkness and might introduce over-exposure distortion in some areas of the enhanced result To alleviate this problem, local histogram-based methods were proposed [5,6]. Jiang et al proposed EnlightenGAN [21] for single image low-light enhancement without paired training data Different from the above methods, Guo et al [25] formulated image enhancement as a task of image-specific curve estimation This method does not require any paired or unpaired training data and directly estimates pixel-wise curve parameters to adjust the input brightness.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have