An efficient framework for deep learning‐based light‐defect image enhancement. Issue 7 (13th January 2021)

• Record Type: Journal Article
• Authors: Ma, Chengxu; Li, Daihui; Zeng, Shangyou; Zhao, Junbo; Chen, Hongyang
• Is Part Of: IET image processing. Volume 15:Issue 7(2021)
• Page Start: 1553
• Page End: 1566
• Publication Date: 2021-01-13
• Subjects: Optical, image and video signal processing -- Computer vision and image processing techniques -- Neural nets; Image processing -- Periodicals; 621.36705
• DOI: 10.1049/ipr2.12125
• Languages: English
• ISSNs: 1751-9659

Abstract

Abstract: The enhancement of light‐defect images such as extremely low‐light, low‐light and dim‐light has always been a research hotspot. Most of the existing methods are excellent in specific illuminations, and there is much room for improvement in processing light‐defect images with different illuminations. Therefore, this study proposes an efficient framework based on deep learning to enhance various light‐defect images. The proposed framework estimates the reflectance component and illumination component. Next, we propose a generator guided by an attention mechanism in the reflectance part to repair the light‐defect in the dark. In addition, we design a colour loss function for the problem of colour distortion in the enhanced images. Finally, the illumination map of the light‐defect images is adjusted adaptively. Extensive experiments are conducted to demonstrate that our method can not only deal with the images with different illuminations but also enhance the images with clearer details and richer colours. At the same time, we prove its superiority by comparing it with state‐of‐the‐art methods under both visual quality comparison and quantitative comparison of various datasets and real‐world images.