A deep convolutional neural network-based low-light image enhancement using illumination map

Liqian Wang; Wenze Shao; Qi Ge

doi:10.1117/12.2557639

Translator Disclaimer

3 January 2020 A deep convolutional neural network-based low-light image enhancement using illumination map

Liqian Wang, Wenze Shao, Qi Ge

Author Affiliations +

Proceedings Volume 11373, Eleventh International Conference on Graphics and Image Processing (ICGIP 2019); 1137311 (2020) https://doi.org/10.1117/12.2557639
Event: Eleventh International Conference on Graphics and Image Processing, 2019, Hangzhou, China

Abstract

This paper proposes a deep convolutional neural network-based low-light image enhancement method. In order to adaptively enhance the image brightness, a convolutional neural network with convolutional modules is designed. Lowlight image is firstly down-sampled into sub-images. Then an illumination map is obtained from the input image to provide additional information to the network. The network works on a tensor that consists of sub-images and illumination map, achieving a good performance in brightness increasing and structure preservation. The enhanced result is reconstructed from the output sub-images. Experimental results demonstrate the effectiveness of the proposed method in low-light image enhancement.

Citation Download Citation

Liqian Wang, Wenze Shao, and Qi Ge "A deep convolutional neural network-based low-light image enhancement using illumination map", Proc. SPIE 11373, Eleventh International Conference on Graphics and Image Processing (ICGIP 2019), 1137311 (3 January 2020); https://doi.org/10.1117/12.2557639

ACCESS THE FULL ARTICLE