LED2Net: Deep Illumination-aware Dehazing with Low-light and Detail Enhancement
This work addresses image quality enhancement for hazy and low-light conditions, which is incremental as it builds on existing retinex theory and CNN-based approaches.
The authors tackled the problem of image dehazing and low-light enhancement by developing a method that uses an illumination map estimated via a CNN, achieving results that surpass recent state-of-the-art algorithms quantitatively and qualitatively, with outputs showing vivid colors and enhanced visibility without halo effects or color distortion.
We present a novel dehazing and low-light enhancement method based on an illumination map that is accurately estimated by a convolutional neural network (CNN). In this paper, the illumination map is used as a component for three different tasks, namely, atmospheric light estimation, transmission map estimation, and low-light enhancement. To train CNNs for dehazing and low-light enhancement simultaneously based on the retinex theory, we synthesize numerous low-light and hazy images from normal hazy images from the FADE data set. In addition, we further improve the network using detail enhancement. Experimental results demonstrate that our method surpasses recent state-of-theart algorithms quantitatively and qualitatively. In particular, our haze-free images present vivid colors and enhance visibility without a halo effect or color distortion.