Images captured in low-light conditions usually suffer from very low contrast, which increases the difficulty of computer vision tasks in a great extent. Existing low-light image restoration methods still have limitation in image naturalness and noise. In this paper, we propose an efficient deep residual network that learns difference map between low-light image and original image and restores the low-light image. Additionally, we propose a new low-light image generator, which is used to train the deep residual network. Especially the proposed generator can simulate low-light images containing luminance sources and completely darkness parts. Our experiments demonstrate that the proposed method achieves good results for both synthetic and natural low-light images.
Song Jun Ri, Hyon Su Choe, Chung Hyok O, Jang Su Kim
Kim Il Sung University, DPR of Korea
Low-Light Image, Image Restoration, Deep Residual Network | Published By :
ICTACT
Published In :
ICTACT Journal on Image and Video Processing
( Volume: 13 , Issue: 3 , Pages: 2899 - 2903 )
Date of Publication :
Feburay 2023
|