Guidance Network with Staged Learning for Image Enhancement

Abstract

Many important yet not fully resolved problems in computational photography and image enhancement, e.g. generating well-lit images from their low-light counterparts or producing RGB images from their RAW camera inputs share a common nature: discovering a color mapping between input pixels to output pixels based on both global information and local details. We propose a novel deep neural network architecture to learn the RAW to RGB mapping based on this common nature. This architecture consists of both global and local sub-networks, where the first sub-network focuses on determining illumination and color mapping, the second sub-network deals with recovering image details. The result of the global network serves as a guidance to the local network to form the final RGB images. Our method outperforms state-of-the-art with a significantly smaller size of network features on various image enhancement tasks.

Cite

Text

Liang et al. "Guidance Network with Staged Learning for Image Enhancement." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2021. doi:10.1109/CVPRW53098.2021.00093

Markdown

[Liang et al. "Guidance Network with Staged Learning for Image Enhancement." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2021.](https://mlanthology.org/cvprw/2021/liang2021cvprw-guidance/) doi:10.1109/CVPRW53098.2021.00093

BibTeX

@inproceedings{liang2021cvprw-guidance,
  title     = {{Guidance Network with Staged Learning for Image Enhancement}},
  author    = {Liang, Luming and Zharkov, Ilya and Amjadi, Faezeh and Joze, Hamid Reza Vaezi and Pradeep, Vivek},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2021},
  pages     = {836-845},
  doi       = {10.1109/CVPRW53098.2021.00093},
  url       = {https://mlanthology.org/cvprw/2021/liang2021cvprw-guidance/}
}