Purifying Low-light Images via Near-Infrared Enlightened Image

Renjie Wan, Boxin Shi, Wenhan Yang, Bihan Wen, Ling-Yu Duan, Alex C. Kot

Research output: Contribution to journalArticlepeer-review


Cameras usually produce low-quality images under low-light conditions. Though many methods have been proposed to enhance the visibility of low-light images, they are mainly designed for illumination correction and less capable of sup-pressing the artifacts. In this paper, we propose to enhance the visibility and suppress artifacts by purifying low-light images under the guidance of the NIR enlightened image captured by using the near-infrared light as compensation. Specifically, we introduce a disentanglement framework to disentangle the structure and color components from the NIR enlightened and RGB images, respectively. Correspondingly, we introduce a new dataset with the RGB and NIR enlightened images for training and evaluation purposes. The experimental results show that our proposed method achieves promising results.
Original languageEnglish
Article number9999306
Pages (from-to)1-13
Number of pages13
JournalIEEE Transactions on Multimedia
Publication statusE-pub ahead of print - 26 Dec 2022

Scopus Subject Areas

  • Signal Processing
  • Electrical and Electronic Engineering
  • Media Technology
  • Computer Science Applications

User-Defined Keywords

  • Cameras
  • Image color analysis
  • Image enhancement
  • Image restoration
  • Lighting
  • Surveillance
  • Training


Dive into the research topics of 'Purifying Low-light Images via Near-Infrared Enlightened Image'. Together they form a unique fingerprint.

Cite this