Multiscale Low-Light Image Enhancement Network With Illumination Constraint

• Published in: IEEE transactions on circuits and systems for video technology Vol. 32; no. 11; pp. 7403 - 7417
• Main Authors: Fan, Guo-Dong, Fan, Bi, Gan, Min, Chen, Guang-Yong, Chen, C. L. Philip
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.11.2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Atmospheric modeling; Color; Computer vision; Deep learning; Distortion; Exposure; Feature extraction; Histograms; Illumination; Image color analysis; Image enhancement; image processing; Light; Light levels; Lighting; Low-light image enhancement; Res2Net; SENet; Source code; Task analysis; U-Net; Visibility; Visual effects
• DOI: 10.1109/TCSVT.2022.3186880
• ISSN: 1051-8215

Images captured under low-light environments typically have poor visibility, affecting many advanced computer vision tasks. In recent years, there have been some low-light image enhancement models based on deep learning, but they have not been able to effectively mine the deep multiscale features in the image, resulting in poor generalization performance and instability of the model. The disadvantages are mainly reflected in the color distortion, color unsaturation and artifacts. Current methods unable to adjust the exposure effectively, resulting in uneven exposure or partial overexposure. To address these issues, we propose an end-to-end low-light image enhancement model, which is called multiscale low-light image enhancement network with illumination constraint (MLLEN-IC), to achieve preferable generalization ability and stable performance. On the one hand, we use the squeeze-and-excitation-Res2Net block (SE-Res2block) as a base unit to enhance the model's ability by extracting deep multiscale features. On the other hand, to make the model more adaptable in low-light image enhancement tasks, we calculate the illumination constraint by the low-light itself to prevent overexposure, uneven exposure, and unsaturated colors. Extensive experiments are conducted to demonstrate MLLEN-IC not only adjusts light levels, but also has a more natural visual effect, and avoids problems such as color distortion, artifacts, and uneven exposure. In particular, MLLEN-IC has pretty generalization and stability performance. The source code and supplementary are available at https://github.com/CCECfgd/MLLEN-IC .