GLADNet: Low-Light Enhancement Network with Global Awareness

TLDR

The paper proposes GLADNet, a network for low‑light image enhancement. GLADNet first estimates global illumination, then refines illumination and reconstructs details using an encoder‑decoder and convolutional network trained on synthetic RAW data. Experiments show GLADNet outperforms existing methods on diverse real low‑light images.

Abstract

In this paper, we address the problem of lowlight enhancement. Our key idea is to first calculate a global illumination estimation for the low-light input, then adjust the illumination under the guidance of the estimation and supplement the details using a concatenation with the original input. Considering that, we propose a GLobal illumination Aware and Detail-preserving Network (GLADNet). The input image is rescaled to a certain size and then put into an encoder-decoder network to generate global priori knowledge of the illumination. Based on the global prior and the original input image, a convolutional network is employed for detail reconstruction. For training GLADNet, we use a synthetic dataset generated from RAW images. Extensive experiments demonstrate the superiority of our method over other compared methods on the real low-light images captured in various conditions.