Qinaty / MBRS

This is the source code of paper MBRS : Enhancing Robustness of DNN-based Watermarking by Mini-Batch of Real and Simulated JPEG Compression, which is received by ACM MM' 21.

MBRS : Enhancing Robustness of DNN-based Watermarking by Mini-Batch of Real and Simulated JPEG Compression

Zhaoyang Jia, Han Fang and Weiming Zhang, from University of Science and Technology of China.

This is the source code of paper MBRS : Enhancing Robustness of DNN-based Watermarking by Mini-Batch of Real and Simulated JPEG Compression, which is received by ACM MM' 21 (oral). Full paper is available in arXiv. Please contact me in issue page or email [e-mail] if you find bugs. Thanks!

usage

Change the settings in json files ./train_settings.json or ./test_settings.json, and run the corresponding .py files for training or testing.

Pre-trained Models

Please download pretrained models in Google Drive and put the in path ./results/xxx/models/.

Others

To be continue ...