Skip to content

Official repository for "RRU-Net: The Ringed Residual U-Net for Image Splicing Forgery Detection" (CVPRW 2019)

Notifications You must be signed in to change notification settings

yelusaleng/RRU-Net

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

25 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

RRU-Net: The Ringed Residual U-Net for Image Splicing Forgery Detection

This repository is for paper "RRU-Net: The Ringed Residual U-Net for Image Splicing Forgery Detection" (CVPR 2019 workshop)

Update (2022.7.31)

I upload the dataset which is used to train RRU-Net in my another repository https://github.com/yelusaleng/SAN_and_HDU-Net.

Update (2022.7.9)

The uploaded model 'best_model' is trained on new datasets generated by my new work "Image splicing forgery detection by combining synthetic adversarial networks and hybrid dense U‐net based on multiple spaces".

@article{Wei2022ImageSF,
  title={Image splicing forgery detection by combining synthetic adversarial networks and hybrid dense U‐net based on multiple spaces},
  author={Yang Wei and Jianfeng Ma and Zhuzhu Wang and Bin Xiao and Wenying Zheng},
  journal={International Journal of Intelligent Systems},
  year={2022}
}

Although the new work was completed two years ago, it was not accepted until recently.

TODO:

  • I will upload the whole project of my new work, it contains a new approach to generate splicing forgery image.

Update (2020.12.15)

Upload the pre-trained model.

NOTICING:

  • the uploaded pre-trained model is trained with new datasets since i lost previous pre-trained model.
  • the new dataset is produced by my new work, so i can't release it currently.

Requirements

  • Python 3.7
  • PyTorch 1.0+
  • CUDA 10.0+

Details

  • './unet/unet-parts.py': it includes detailed implementations of 'U-Net', 'RU-Net' and 'RRU-Net'
  • 'train.py': you can use it to train your model
  • 'predict.py': you can use it to test

Citation

Please add following information if you cite the paper in your publication:

@inproceedings{bi2019rru,
  title={RRU-Net: The Ringed Residual U-Net for Image Splicing Forgery Detection},
  author={Bi, Xiuli and Wei, Yang and Xiao, Bin and Li, Weisheng},
  booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops},
  pages={0--0},
  year={2019}
}

Contact yale ywei9395@gmail.com for any further information.

About

Official repository for "RRU-Net: The Ringed Residual U-Net for Image Splicing Forgery Detection" (CVPRW 2019)

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages