An efficient framework for deep learning‐based light‐defect image enhancement
Chengxu Ma, Daihui Li, Shangyou Zeng et al. · IET Image Processing · 2021
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.
Cited by 5 works. doi:10.1049/ipr2.12125 Open-access PDF
Authors
References
- U-Net: Convolutional Networks for Biomedical Image Segmentation
- Image quality assessment: from error visibility to structural similarity
- UNet++: A Nested U-Net Architecture for Medical Image Segmentation
- The Retinex Theory of Color Vision
- A multiscale retinex for bridging the gap between color images and the human observation of scenes
- Making a “Completely Blind” Image Quality Analyzer
- Properties and performance of a center/surround retinex
- LIME: Low-Light Image Enhancement via Illumination Map Estimation
- Real-Time Compressive Tracking
- Loss Functions for Image Restoration With Neural Networks