Skip to content

MATLAB Implementation of CVPR 2019 paper <<On Finding Gray Pixels>>

License

Notifications You must be signed in to change notification settings

yanlinqian/Grayness-Index

Repository files navigation

On Finding Gray Pixels

Matlab Code accompanying the paper On Finding Gray Pixels. [arXiv]

Intro

From left to right: (a) input image. (b) computed grayness index GI. darker blue indicates higher degree of grayness. (c) the N % most gray pixels rendered using the corresponding pixel color (greenish) in (a). (d) estimated illumination color. (e) ground truth color. (f) corrected image using (d).

If you use grayness index code or results, please consider citing following paper:

@inproceedings{qian2019cvpr,
  title={On Finding Gray Pixels},
  author={Qian, Yanlin and K{\"a}m{\"a}r{\"a}inen, Joni-Kristian and Nikkanen, Jarno and Matas, Jiri},
  booktitle={IEEE International Conference of Computer Vision and Pattern Recognition},
  year={2019}
}

If you use classic gray pixel code or results, please consider citing following paper:

@inproceedings{yang2015efficient,
  title={Efficient illuminant estimation for color constancy using grey pixels},
  author={Yang, Kai-Fu and Gao, Shao-Bing and Li, Yong-Jie},
  booktitle={CVPR},
  year={2015}
}

If you use mean-shifted gray pixel code or results ([here] ), please consider citing following paper:

@inproceedings{qian2019vissap,
  title={Revisiting Gray Pixel for Statistical Illumination Estimation},
  author={Qian, Yanlin and Purtuz, Said and Nikkanen, Jarno and K{\"a}m{\"a}r{\"a}inen, Joni-Kristian and Matas, Jiri},
  booktitle={International Conference of Computer Vision Theory and Applications},
  year={2019}
}

Releases

No releases published

Packages

No packages published