This repository is for paper "RRU-Net: The Ringed Residual U-Net for Image Splicing Forgery Detection" (CVPR 2019 workshop)
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.
- Python 3.7
- PyTorch 1.0+
- CUDA 10.0+
- './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
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 yalesaleng@gmail.com for any further information.