English

Fearless Luminance Adaptation: A Macro-Micro-Hierarchical Transformer for Exposure Correction

Computer Vision and Pattern Recognition 2023-12-19 v2

Abstract

Photographs taken with less-than-ideal exposure settings often display poor visual quality. Since the correction procedures vary significantly, it is difficult for a single neural network to handle all exposure problems. Moreover, the inherent limitations of convolutions, hinder the models ability to restore faithful color or details on extremely over-/under- exposed regions. To overcome these limitations, we propose a Macro-Micro-Hierarchical transformer, which consists of a macro attention to capture long-range dependencies, a micro attention to extract local features, and a hierarchical structure for coarse-to-fine correction. In specific, the complementary macro-micro attention designs enhance locality while allowing global interactions. The hierarchical structure enables the network to correct exposure errors of different scales layer by layer. Furthermore, we propose a contrast constraint and couple it seamlessly in the loss function, where the corrected image is pulled towards the positive sample and pushed away from the dynamically generated negative samples. Thus the remaining color distortion and loss of detail can be removed. We also extend our method as an image enhancer for low-light face recognition and low-light semantic segmentation. Experiments demonstrate that our approach obtains more attractive results than state-of-the-art methods quantitatively and qualitatively.

Keywords

Cite

@article{arxiv.2309.00872,
  title  = {Fearless Luminance Adaptation: A Macro-Micro-Hierarchical Transformer for Exposure Correction},
  author = {Gehui Li and Jinyuan Liu and Long Ma and Zhiying Jiang and Xin Fan and Risheng Liu},
  journal= {arXiv preprint arXiv:2309.00872},
  year   = {2023}
}

Comments

Accepted by ACM MM 2023

R2 v1 2026-06-28T12:11:00.089Z