https://github.com/zuruoke/watermark-removal

a machine learning image inpainting task that instinctively removes watermarks from image indistinguishable from the ground truth image
https://github.com/zuruoke/watermark-removal

deep-learning machine-learning python tensorflow watermark-image

Last synced: 5 days ago
JSON representation

a machine learning image inpainting task that instinctively removes watermarks from image indistinguishable from the ground truth image

• Host: GitHub
• URL: https://github.com/zuruoke/watermark-removal
• Owner: zuruoke
• Created: 2021-11-04T07:27:37.000Z (over 3 years ago)
• Default Branch: master
• Last Pushed: 2024-08-16T13:14:47.000Z (6 months ago)
• Last Synced: 2025-01-30T08:05:54.728Z (12 days ago)
• Topics: deep-learning, machine-learning, python, tensorflow, watermark-image
• Language: Python
• Homepage:
• Size: 41 KB
• Stars: 2,265
• Watchers: 25
• Forks: 333
• Open Issues: 34
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
Chimzuruoke Okafor

# Watermark-Removal



  

  

  



![version](https://img.shields.io/badge/version-v1.0.0-green.svg?style=plastic)

![pytorch](https://img.shields.io/badge/tensorflow-v1.15.0-green.svg?style=plastic)

![license](https://img.shields.io/badge/license-CC_BY--NC-green.svg?style=plastic)

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

- 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

## 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