ColorNet - Estimating colorfulness in natural images

Sample figure showing the model structure and qualitative test results.

Overview

This repository provides the code and the pre-trained models for the following paper:

   "ColorNet – Estimating colorfulness in natural images"
   Emin Zerman*, Aakanksha Rana*, Aljosa Smolic
   IEEE International Conference on Image Processing (ICIP), Taipei, Taiwan, September 2019.

*These authors contributed equally to this work.

You can find the paper on IEEEXplore servers and the preprint on our project webpage or on arXiv.

Citing

If you use this code or one of these models, please cite our paper:

@inproceedings{zerman2019colornet,
  author       = {Zerman, Emin and Rana, Aakanksha and Smolic, Aljosa},
  title        = {{ColorNet} - Estimating colorfulness in natural images},
  booktitle    = {International Conference on Image Processing ({ICIP})},
  month        = {Sept},
  year         = {2019},
  publisher    = {IEEE}
}

Acknowledgements

This publication has emanated from research conducted with the financial support of Science Foundation Ireland (SFI) under the Grant Number 15/RP/2776. We also gratefully acknowledge the support of NVIDIA Corporation with the donated GPU used for this research.

License

This code and the models are licenced under GNU GPLv3.0. Please check the LICENCE file for more details.