Learning Lightweight Low-Light Enhancement Network Using Pseudo Well-Exposed Images

Seonggwan Ko, Jinsun Park, Byungjoo Chae, Donghyeon ChoIEEE Signal Processing Letters 2022 · DOI · OpenReview

Abstract

Recently, there has been growing attention on deep learning-based low-light image enhancement algorithms. With this interest, various synthetic low-light image datasets have been released publicly. However, real-world low-light and well-exposed image pair datasets are still lacking. In this paper, we propose a real-world low-light image dataset and a practical lightweight low-light image enhancement network. In order to construct a large-scale real-world low-light dataset, we have not only captured under-exposed images by ourselves but also collected under-exposed images from the Internet. Then, we produce pseudo well-exposed images for each low-light image. Using pairs of a real-world low-light image and a pseudo well-exposed image, we present a lightweight deep CNN model through knowledge distillation. Experimental results demonstrate the effectiveness and practicality of the proposed method on various datasets.
BibTeX
@article{ko2022learning,
  author = {Seonggwan Ko and Jinsun Park and Byungjoo Chae and Donghyeon Cho},
  title = {{Learning Lightweight Low-Light Enhancement Network Using Pseudo Well-Exposed Images}},
  journal = {IEEE Signal Processing Letters},
  year = {2022},
  doi = {10.1109/lsp.2021.3134943},
}

Loading related content...

Figure