S-Dust


The S-Dust dataset is part of our paper: “Semantic Segmentation and Inpainting of Dust with the S-Dust Dataset”.

S-Dust provides 963 images from two fields with a resolution of 3820 x 2160 pixels taken with a GoPro Hero 4.

Dataset

If you are going to use S-Dust dataset, please cite:

@article{buckel2023semantic,
  title={Semantic Segmentation and Inpainting of Dust with the S-Dust Dataset},
  author={Buckel, Peter and Oksanen, Timo and Dietmueller, Thomas},
  journal={IFAC-PapersOnLine},
  volume={56},
  number={2},
  pages={8896--8901},
  year={2023},
  publisher={Elsevier}
}

License

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.