Low-light image enhancement network based on multi-stream information supplement

• Published in: Multidimensional systems and signal processing Vol. 33; no. 3; pp. 711 - 723
• Main Authors: Yang, Yong, Hu, Wei, Huang, Shuying, Tu, Wei, Wan, Weiguo
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.09.2022; Springer Nature B.V
• Subjects: Algorithms; Artificial Intelligence; Circuits and Systems; Color; Electrical Engineering; Engineering; Image enhancement; Image restoration; Signal,Image and Speech Processing; Multi-stream information supplement; Joint loss function; Low-light image enhancement
• ISSN: 0923-6082; 1573-0824
• DOI: 10.1007/s11045-021-00812-w

Images captured under low-light conditions often suffer from severe loss of structural details and color; therefore, image-enhancement algorithms are widely used in low-light image restoration. Image-enhancement algorithms based on the traditional Retinex model only consider the change in the image brightness, while ignoring the noise and color deviation generated during the process of image restoration. In view of these problems, this paper proposes an image enhancement network based on multi-stream information supplement, which contains a mainstream structure and two branch structures with different scales. To obtain richer feature information, an information complementary module is designed to realize the information supplement for the three structures. The feature information from the three structures is then concatenated to perform the final image recovery operation. To restore more abundant structures and realistic colors, we define a joint loss function by combining the L1 loss, structural similarity loss, and color-difference loss to guide the network training. The experimental results show that the proposed network achieves satisfactory performance in both subjective and objective aspects.