A Comparative Analysis of Deep Learning based Approaches for Low-Light Image Enhancement

Images clicked under low and non-uniform light conditions are visually unpleasant and lose details. Low-light images also impact the performance and thus reduce the effectiveness of various computer vision tasks. Thus numerous methods have been put forward in the past to upgrade the quality of low-light images. The innovations in the field of deep learning have paved the way for the application of neural networks to the task of enhancing low-light images. In this paper, we offer a comparative analysis of various approaches using deep learning for enhancing low-light images. We explore retinex based methods including KinD and RDGAN, and other non-retinex based methods including LLNet, GLAD Net, and Zero-DCE. We measure the effectiveness of these methods on various datasets and provide their advantages and disadvantages.