Satellite Image Dehazing via Masked Image Modeling and Jigsaw Transformation

Abstract

In this paper, we successfully apply masked image modeling (MIM) to the dehazing process for satellite images, introducing a novel dehazing method. Initially, we investigate why MIM does not effectively function as a self-supervised learning method for low-level vision tasks and fails to yield improved performance. Subsequently, we propose two solutions to address this issue. Furthermore, we introduce an augmentation technique that enhances both locality and non-locality in puzzle images through jigsaw transformations, resulting in improved accuracy. Experimental results show that our method outperforms other state-of-the-art methods, including approaches based on visual transformers.

Cite

Text

Kim et al. "Satellite Image Dehazing via Masked Image Modeling and Jigsaw Transformation." European Conference on Computer Vision Workshops, 2024. doi:10.1007/978-3-031-91838-4_27

Markdown

[Kim et al. "Satellite Image Dehazing via Masked Image Modeling and Jigsaw Transformation." European Conference on Computer Vision Workshops, 2024.](https://mlanthology.org/eccvw/2024/kim2024eccvw-satellite/) doi:10.1007/978-3-031-91838-4_27

BibTeX

@inproceedings{kim2024eccvw-satellite,
  title     = {{Satellite Image Dehazing via Masked Image Modeling and Jigsaw Transformation}},
  author    = {Kim, Guisik and Cho, Choongsang and Kwon, Junseok},
  booktitle = {European Conference on Computer Vision Workshops},
  year      = {2024},
  pages     = {449-466},
  doi       = {10.1007/978-3-031-91838-4_27},
  url       = {https://mlanthology.org/eccvw/2024/kim2024eccvw-satellite/}
}