watermark-removal

Chimzuruoke Okafor # Watermark-Removal

An open source project that uses a machine learning based image inpainting methodology to remove watermark from images which is totally indistinguishable from the ground truth version of the image. This project was inspired by the [Contextual Attention](https://arxiv.org/abs/1801.07892) (CVPR 2018) and [Gated Convolution](https://arxiv.org/abs/1806.03589) (ICCV 2019 Oral). And also a shoutout to [Chu-Tak Li](https://chutakcode.wixsite.com/website) for his [Medium article series](https://towardsdatascience.com/10-papers-you-must-read-for-deep-image-inpainting-2e41c589ced0) that really gave me a deep insight into the image inpainting papers stated above ## Run ### Docker 1. Clone this repository to your computer. 2. From the repository root, build a Docker image with the command `docker build -t watermark-removal .` 3. Download the model dir using this [link](https://drive.google.com/drive/folders/1xRV4EdjJuAfsX9pQme6XeoFznKXG0ptJ?usp=sharing). 4. Create and run a docker container with the image you built using the command: ```bash docker run --rm -v ':/repo/model' -v ':/input' -v ':/output' watermark-removal --checkpoint_dir /repo/model --image '/input/' --output '/output/' --watermark_type istock ``` ### Google colab (broken) - use [Google colab](https://research.google.com/colaboratory/) - First of all, clone this repo !git clone https://github.com/zuruoke/watermark-removal - Change Directory to the repo !cd watermark-removal - Since Google Colab uses the latest Tensorflow 2x version and this project uses 1.15.0, downgrade to Tensorflow 1.15.0 version and restart the runtime, (`although the new version of Google Colab does not need you to restart the runtime`). !pip install tensorflow==1.15.0 - Install tensorflow toolkit [neuralgym](https://github.com/JiahuiYu/neuralgym). !pip install git+https://github.com/JiahuiYu/neuralgym - Download the model dirs using this [link](https://drive.google.com/drive/folders/1xRV4EdjJuAfsX9pQme6XeoFznKXG0ptJ?usp=sharing) and put it under `model/` (rename `checkpoint.txt` to `checkpoint` because sometimes google drive automatically adds .txt after download) And you're all Set!! - Now remove the watermark on the image by runing the `main.py` file !python main.py --image path-to-input-image --output path-to-output-image --checkpoint_dir model/ --watermark_type istock ## Citation If you use this in your research, please cite: Zuruoke (2021). _Watermark Removal: a machine learning image inpainting task_. GitHub Repository. https://doi.org/10.5281/zenodo.20551267 ## Citing ``` @article{yu2018generative, title={Generative Image Inpainting with Contextual Attention}, author={Yu, Jiahui and Lin, Zhe and Yang, Jimei and Shen, Xiaohui and Lu, Xin and Huang, Thomas S}, journal={arXiv preprint arXiv:1801.07892}, year={2018} } @article{yu2018free, title={Free-Form Image Inpainting with Gated Convolution}, author={Yu, Jiahui and Lin, Zhe and Yang, Jimei and Shen, Xiaohui and Lu, Xin and Huang, Thomas S}, journal={arXiv preprint arXiv:1806.03589}, year={2018} } ```

## © Chimzuruoke Okafor