Image inpainting using OpenCV & DeepFillv2 (places2, celebahq) on Streamlit

The project was created to demonstrate tools for restoring voids in an image (not generating)

Created for my friend.

Example

By default, the app prompts you to upload your image or use your webcam.

Next you create a mask by drawing on the image.

Click the "Fill the blanks" button and get the result.

You can also see the values of the following metrics: PNSR, MSE, SSIM.

Run app

Clone the repository

git clone https://github.com/Mariama4/tea_image_inpainting.git

Install dependencies

pip install -r requirements.txt

Start the application

streamlit run main_page.py

Links

1. https://streamlit.io/

2. https://www.olivier-augereau.com/docs/2004JGraphToolsTelea.pdf

3. https://www.researchgate.net/publication/3940597_Navier-Stokes_fluid_dynamics_and_image_and_video_inpainting

4. https://github.com/nipponjo/deepfillv2-pytorch