Band Representation-Based Semi-Supervised Low-Light Image Enhancement: Bridging the Gap Between Signal Fidelity and Perceptual Quality

2021 ◽  
pp. 1-1
Author(s):  
Wenhan Yang ◽  
Shiqi Wang ◽  
Yuming Fang ◽  
Yue Wanga ◽  
Jiaying Liu
Keyword(s):  
Image Enhancement ◽  
Perceptual Quality ◽  
Low Light ◽  
Light Image

Perceptual Quality Assessment of Low-light Image Enhancement

2021 ◽  
Vol 17 (4) ◽  
pp. 1-24
Author(s):  
Guangtao Zhai ◽  
Wei Sun ◽  
Xiongkuo Min ◽  
Jiantao Zhou
Keyword(s):  
Image Quality ◽  
Quality Assessment ◽  
Image Enhancement ◽  
Dynamic Range ◽  
State Of The Art ◽  
Perceptual Quality ◽  
Low Light ◽  
Light Image ◽  
Light Enhancement

Low-light image enhancement algorithms (LIEA) can light up images captured in dark or back-lighting conditions. However, LIEA may introduce various distortions such as structure damage, color shift, and noise into the enhanced images. Despite various LIEAs proposed in the literature, few efforts have been made to study the quality evaluation of low-light enhancement. In this article, we make one of the first attempts to investigate the quality assessment problem of low-light image enhancement. To facilitate the study of objective image quality assessment (IQA), we first build a large-scale low-light image enhancement quality (LIEQ) database. The LIEQ database includes 1,000 light-enhanced images, which are generated from 100 low-light images using 10 LIEAs. Rather than evaluating the quality of light-enhanced images directly, which is more difficult, we propose to use the multi-exposure fused (MEF) image and stack-based high dynamic range (HDR) image as a reference and evaluate the quality of low-light enhancement following a full-reference (FR) quality assessment routine. We observe that distortions introduced in low-light enhancement are significantly different from distortions considered in traditional image IQA databases that are well-studied, and the current state-of-the-art FR IQA models are also not suitable for evaluating their quality. Therefore, we propose a new FR low-light image enhancement quality assessment (LIEQA) index by evaluating the image quality from four aspects: luminance enhancement, color rendition, noise evaluation, and structure preserving, which have captured the most key aspects of low-light enhancement. Experimental results on the LIEQ database show that the proposed LIEQA index outperforms the state-of-the-art FR IQA models. LIEQA can act as an evaluator for various low-light enhancement algorithms and systems. To the best of our knowledge, this article is the first of its kind comprehensive low-light image enhancement quality assessment study.

scholarly journals A Switched View of Retinex: Deep Self-Regularized Low-Light Image Enhancement

2021 ◽  
Author(s):  
Zhuqing Jiang ◽  
Haotian Li ◽  
Liangjie Liu ◽  
Aidong Men ◽  
Haiying Wang
Keyword(s):  
Image Enhancement ◽  
Low Light ◽  
Light Image

scholarly journals Multi-Feature Guided Low-Light Image Enhancement

2021 ◽  
Vol 11 (11) ◽  
pp. 5055
Author(s):  
Hong Liang ◽  
Ankang Yu ◽  
Mingwen Shao ◽  
Yuru Tian
Keyword(s):  
Image Enhancement ◽  
Signal To Noise Ratio ◽  
Low Light ◽  
Low Contrast ◽  
Light Image ◽  
Affine Model ◽  
The Neural Network ◽  
Low Visibility ◽  
Model Robustness ◽  
Traditional Image

Due to the characteristics of low signal-to-noise ratio and low contrast, low-light images will have problems such as color distortion, low visibility, and accompanying noise, which will cause the accuracy of the target detection problem to drop or even miss the detection target. However, recalibrating the dataset for this type of image will face problems such as increased cost or reduced model robustness. To solve this kind of problem, we propose a low-light image enhancement model based on deep learning. In this paper, the feature extraction is guided by the illumination map and noise map, and then the neural network is trained to predict the local affine model coefficients in the bilateral space. Through these methods, our network can effectively denoise and enhance images. We have conducted extensive experiments on the LOL datasets, and the results show that, compared with traditional image enhancement algorithms, the model is superior to traditional methods in image quality and speed.

Sign in / Sign up

Export Citation Format

Share Document