ML Anthology

Gamma-Enhanced Spatial Attention Network for Efficient High Dynamic Range Imaging

Fangya Li, Ruipeng Gang, Chenghua Li, Jinjing Li, Sai Ma, Chenming Liu, Yizhen Cao
CVPRW 2022 pp. 1031-1039
doi:10.1109/CVPRW56347.2022.00116 /cvprw/2022/li2022cvprw-gammaenhanced/

Abstract

High dynamic range(HDR) imaging is the task of re-covering HDR image from one or multiple input Low Dynamic Range (LDR) images. In this paper, we present Gamma-enhanced Spatial Attention Network(GSANet), a novel framework for reconstructing HDR images. This problem comprises two intractable challenges of how to tackle overexposed and underexposed regions and how to overcome the paradox of performance and complexity trade-off. To address the former, after applying gamma correction on the LDR images, we adopt a spatial attention module to adaptively select the most appropriate regions of various exposure low dynamic range images for fusion. For the latter one, we propose an efficient channel attention module, which only involves a handful of parameters while bringing clear performance gain. Experimental results show that the proposed method achieves better visual quality on the HDR dataset. The code will be available at: https://github.com/fancyicookie/GSANet

CVPRW Semantic Scholar

Cite

Text

Li et al. "Gamma-Enhanced Spatial Attention Network for Efficient High Dynamic Range Imaging." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2022. doi:10.1109/CVPRW56347.2022.00116

Markdown

[Li et al. "Gamma-Enhanced Spatial Attention Network for Efficient High Dynamic Range Imaging." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2022.](https://mlanthology.org/cvprw/2022/li2022cvprw-gammaenhanced/) doi:10.1109/CVPRW56347.2022.00116

BibTeX

@inproceedings{li2022cvprw-gammaenhanced,
  title     = {{Gamma-Enhanced Spatial Attention Network for Efficient High Dynamic Range Imaging}},
  author    = {Li, Fangya and Gang, Ruipeng and Li, Chenghua and Li, Jinjing and Ma, Sai and Liu, Chenming and Cao, Yizhen},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2022},
  pages     = {1031-1039},
  doi       = {10.1109/CVPRW56347.2022.00116},
  url       = {https://mlanthology.org/cvprw/2022/li2022cvprw-gammaenhanced/}
}