Image Colorization and Outpainting

This project focuses on image colorization and outpainting using various GAN-based models like Pix2Pix, DeepLab, PatchGAN with U-Net, and Encoder-Decoder networks. It offers functionalities for colorizing grayscale images and expanding image boundaries seamlessly.

Features

• Image Colorization: Convert grayscale images into realistic color versions using different models like Pix2Pix, DeepLab, and PatchGAN with U-Net.
• Outpainting: Expand image boundaries using an Encoder-Decoder network, allowing for seamless content generation beyond the input image.
• Blending and Sharpening: Apply blending techniques for smooth transitions and sharpen outpainted regions for a more refined look.

Getting Started

Follow the steps below to set up and run the project locally.

Prerequisites

• Python 3.x
• pip (Python package installer)
• Download the model and put them in respective folders -link: https://drive.google.com/drive/folders/1ZUf5rMwsi3Xz0FzB-rB3CHmCfguEMVdR?usp=sharing

Installation

1. Clone the repository

   git clone https://github.com/nit-1418/Image_Colorization_and_Outpainting.git

2. Navigate to the project directory:

     cd Image_Colorization_and_Outpainting

3. Install dependencies

   pip install -r requirements.txt

4. Run the application

   python app.py

Contributing

• Special thanks to
• Shlok Koirala: https://github.com/shlok-py
• Anshu Patel: https://github.com/napsnu
• for valuable contribution in Colorization models.
• Also Open Contributions are welcome! Feel free to fork the repository, create a new branch, and submit a pull request. Please ensure your changes are well-documented.