Dimma: Semi-Supervised Low-Light Image Enhancement with Adaptive Dimming

Authors:
Open Access
Publisher website
Google Scholar
Abstract
Enhancing low-light images with natural colors poses a challenge due to camera processing variations and limited access to ground-truth lighting conditions. To address this, we propose Dimma, a semi-supervised approach that aligns with any camera using a small set of image pairs captured under extreme lighting conditions. Our method employs a convolutional mixture density network to replicate camera-specific noise present in dark images. We enhance results further by introducing a conditional UNet architecture based on user-provided lightness values. Trained on just a few real image pairs, Dimma achieves competitive results compared to fully supervised state-of-the-art methods trained on large datasets.
Funding Information
  • National Centre of Science (Poland) (2021/43/B/ST6/02853, PLG/2023/016646)
  • Polish high-performance computing infrastructure PLGrid (HPC Centers: ACK Cyfronet AGH, CI TASK) (2021/43/B/ST6/02853, PLG/2023/016646)

This publication has 23 references indexed in Scilit: