8000
Skip to content

Repository files navigation

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.

Uploading an image

Next you create a mask by drawing on the image.

Снимок экрана 2024-04-17 в 15.52.02

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

Снимок экрана 2024-04-17 в 15.52.23 Снимок экрана 2024-04-17 в 15.52.31

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

Снимок экрана 2024-04-17 в 15.52.39

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

About

Image inpainting using OpenCV & DeepFillv2

Topics

Resources

Stars

1 star

Watchers

1 watching

Forks

Releases

Packages

Used by

Contributors

Languages

0