Unsupervised Low-Light Image Enhancement Using Bright Channel Prior

Hunsang Lee, Kwanghoon Sohn, Dongbo Min

Research output: Contribution to journalArticlepeer-review

69 Scopus citations


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.

Original languageEnglish
Article number8955834
Pages (from-to)251-255
Number of pages5
JournalIEEE Signal Processing Letters
StatePublished - 2020

Bibliographical note

Publisher Copyright:
© 1994-2012 IEEE.


  • Unsupervised learning
  • bright channel prior
  • low-light image enhancement


Dive into the research topics of 'Unsupervised Low-Light Image Enhancement Using Bright Channel Prior'. Together they form a unique fingerprint.

Cite this