https://github.com/bytedance/dwsf
code repository for Practical Deep Dispersed Watermarking with Synchronization
Science Score: 23.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
○CITATION.cff file
-
○codemeta.json file
-
○.zenodo.json file
-
✓DOI references
Found 1 DOI reference(s) in README -
✓Academic publication links
Links to: acm.org -
○Committers with academic emails
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (8.6%) to scientific vocabulary
Keywords
Repository
code repository for Practical Deep Dispersed Watermarking with Synchronization
Basic Info
Statistics
- Stars: 69
- Watchers: 7
- Forks: 12
- Open Issues: 6
- Releases: 0
Topics
Metadata Files
README.md
Practical Deep Dispersed Watermarking with Synchronization and Fusion
This repository is the official implementation of Practical Deep Dispersed Watermarking with Synchronization and Fusion.
Introduction
This paper focuses on two important and practical aspects that are not well addressed in existing deep learning based works, i.e., embedding in arbitrary resolution (especially high resolution) images, and robustness against complex attacks. To overcome these limitations, we propose a blind watermarking framework (called DWSF) which mainly consists of three novel components, i.e., dispersed embedding, watermark synchronization and message fusion.
Dependencies
environment
python 3.7.3
torch 1.10.0
numpy 1.21.6
Pillow 9.1.1
tqdm 4.64.1
kornia 0.6.8
crc8 0.1.0
opencv-python 4.6.0.66
torchsummary 1.5.1
torchvision 0.11.1
dataset
Usage
training
train encoderdecoder
```
python trained.py --traindatasetpath traindatasetpath --valdatasetpath valdatasetpath --savepath pthoutput_path
train segmentation model
generate watermarked image and mask
python generatesegdata.py --imgpath originalimagepath --outpath watermarkedimgmaskpath --weightpath encoderdecoderpthpath
train segmentation mode
python trainseg.py --trainpath trainwatermarkedimgmaskpath --testpath testwatermarkedimgmaskpath --outputpath pthoutputpath ```
evaluating
python evaluate.py --ori_path original_image_path --pth_path encoder_decoder_pth_path --out_path output_path
citation
If you find this work useful, please cite our paper:
@inproceedings{guo2023practical,
title={Practical Deep Dispersed Watermarking with Synchronization and Fusion},
author={Guo, Hengchang and Zhang, Qilong and Luo, Junwei and Guo, Feng and Zhang, Wenbin and Su, Xiaodong and Li, Minglei},
booktitle={Proceedings of the 31st ACM International Conference on Multimedia},
pages={7922--7932},
year={2023}
}
Owner
- Name: Bytedance Inc.
- Login: bytedance
- Kind: organization
- Location: Singapore
- Website: https://opensource.bytedance.com
- Twitter: ByteDanceOSS
- Repositories: 255
- Profile: https://github.com/bytedance
GitHub Events
Total
- Issues event: 1
- Watch event: 15
- Issue comment event: 1
- Pull request event: 1
- Fork event: 5
Last Year
- Issues event: 1
- Watch event: 15
- Issue comment event: 1
- Pull request event: 1
- Fork event: 5
Issues and Pull Requests
Last synced: 11 months ago
All Time
- Total issues: 4
- Total pull requests: 1
- Average time to close issues: N/A
- Average time to close pull requests: N/A
- Total issue authors: 4
- Total pull request authors: 1
- Average comments per issue: 2.0
- Average comments per pull request: 0.0
- Merged pull requests: 0
- Bot issues: 0
- Bot pull requests: 0
Past Year
- Issues: 2
- Pull requests: 1
- Average time to close issues: N/A
- Average time to close pull requests: N/A
- Issue authors: 2
- Pull request authors: 1
- Average comments per issue: 0.0
- Average comments per pull request: 0.0
- Merged pull requests: 0
- Bot issues: 0
- Bot pull requests: 0
Top Authors
Issue Authors
- chenmingyue6 (1)
- thisisanameso (1)
- CZwalker (1)
- luizz8416 (1)
Pull Request Authors
- Cherrling (1)