Skip to content

Project page for the paper Semi-Supervised Raw-to-Raw Mapping 2021.

Notifications You must be signed in to change notification settings

mahmoudnafifi/raw2raw

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 

Repository files navigation

Semi-Supervised Raw-to-Raw Mapping

Mahmoud Afifi and Abdullah Abuolaim

York University

Project page of the paper Semi-Supervised Raw-to-Raw Mapping. Mahmoud Afifi and Abdullah Abuolaim. arXiv preprint arXiv:2106.13883, 2021. If you use this code, please cite our paper:

@article{afifi2021raw2raw,
  title={Semi-Supervised Raw-to-Raw Mapping},
  author={Afifi, Mahmoud and Abuolaim, Abdullah},
  journal={arXiv preprint arXiv:2106.13883},
  year={2021}
}

teaser

Dataset

Our dataset consists of an unpaired and paired set of images captured by two different smartphone cameras: Samsung Galaxy S9 and iPhone X. The unpaired set includes 196 images captured by each smartphone camera (total of 392). The paired set includes 115 pair of images used for testing. In addition to this paired set, we have another small set of 22 anchor paired images. See our paper for more details.

dataset_examples

Original DNG files of our raw images, in addition to the associated source code to extract raw images and metadata, will be released soon.

MIT License

Releases

No releases published

Packages

No packages published

Languages