An Effective Network with ConvLSTM for Low-Light Image Enhancement

Abstract

Low-light image enhancement is a fundamental problem in computer vision. The artifact, noise, insufficient contrast and color distortion are common challenging problems in low-light image enhancement. In this paper, we present a convolutional Long Short-Term Memory (ConvLSTM) network based method to directly restore a normal image from a low-light image, which can be learned in an end-to-end way. Specifically, our base network employs the encoder-decoder structure. Meanwhile, considering that a normal image may correspond to low-light images of different illuminance levels, we adopt a multi-branch structure combined with ConvLSTM to solve this problem. The extensive experiments on two low-light datasets show that our method outperforms the state-of-the-art traditional and deep learning based methods vertified by both quantitative and qualitative evaluation.