Unsupervised Low-Light Image Enhancement Using Bright Channel Prior
- 주제(키워드) Unsupervised learning , low-light image enhancement , bright channel prior
- 주제(기타) Engineering, Electrical & Electronic
- 설명문(일반) [Lee, Hunsang; Sohn, Kwanghoon] Yonsei Univ, Sch Elect & Elect Engn, Seoul 03722, South Korea; [Min, Dongbo] Chungnam Natl Univ, Daejeon 34134, South Korea; [Min, Dongbo] Ewha Womans Univ, Dept Comp Sci & Engn, Seoul 03760, South Korea
- 관리정보기술 faculty
- 등재 SCIE, SCOPUS
- 발행기관 IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
- 발행년도 2020
- 총서유형 Journal
- URI http://www.dcollection.net/handler/ewha/000000169461
- 본문언어 영어
- Published As https://dx.doi.org/10.1109/LSP.2020.2965824
초록/요약
Recent approaches for low-light image enhancement achieve excellent performance through supervised learning based on convolutional neural networks. However, it is still challenging to collect a large amount of low-/normal-light image pairs in real environments for training the networks. In this letter, we propose an unsupervised learning approach for single low-light image enhancement using the bright channel prior (BCP) that the brightest pixel in a small patch is likely to be close to 1. An unsupervised loss function is defined with the pseudo ground-truth generated using the BCP. An enhancement network, consisting of a simple encoder-decoder, is then trained using the unsupervised loss function. To the best of our knowledge, this is the first attempt that enhances a low-light image through unsupervised learning. Furthermore, we introduce saturation loss and self-attention map for preserving image details and naturalness in the enhanced result. The performance of the proposed method is validated on various public datasets. Experimental results demonstrate that the proposed unsupervised approach achieves competitive performance over state-of-the-art methods based on supervised learning.
more