Low-FaceNet: Face Recognition-driven Low-light Image Enhancement

Yihua FAN, Yongzhen WANG, Dong LIANG, Yiping CHEN, Haoran XIE, Fu Lee WANG, Jonathan LI, Mingqiang WEI

Research output: Journal PublicationsJournal Article (refereed)peer-review


Images captured in low-light conditions often induce the performance degradation of cutting-edge face recognition models. The missing and wrong face recognition inevitably makes vision-based systems operate poorly. In this paper, we propose Low-FaceNet, a novel face recognition-driven network to make low-level image enhancement (LLE) interact with high-level recognition for realizing mutual gain under a unified deep learning framework. Unlike existing methods, Low-FaceNet uniquely brightens real-world images by unsupervised contrastive learning and absorbs the wisdom of facial understanding. Low-FaceNet possesses an image enhancement network that is assembled by four key modules: a contrastive learning module, a feature extraction module, a semantic segmentation module, and a face recognition module. These modules enable Low-FaceNet to not only improve the brightness contrast and retain features but also increase the accuracy of recognizing faces in low-light conditions. Furthermore, we establish a new dataset of low-light face images called LaPa-Face. It includes detailed annotations with 11 categories of facial features and identity labels. Extensive experiments demonstrate our superiority against state-of-the-art methods of both LLE and face recognition even without ground-truth image labels. Our code and dataset are available at https://github.com/fanyihua0309/Low-FaceNet.
Original languageEnglish
JournalIEEE Transactions on Instrumentation and Measurement
Publication statusE-pub ahead of print - 21 Mar 2024

Bibliographical note

Publisher Copyright:


  • Face recognition
  • Image enhancement
  • Image recognition
  • Lighting
  • Low-FaceNet
  • Semantics
  • Task analysis
  • Training
  • contrastive learning
  • face recognition
  • low-light image enhancement
  • semantic segmentation


Dive into the research topics of 'Low-FaceNet: Face Recognition-driven Low-light Image Enhancement'. Together they form a unique fingerprint.

Cite this