Supercolor is an ML web-app which has been trained to rebuild color images from their grayscale or B/W input equivalents that you provide us with.
- Demo:
- Browse images from your system and try out our image colorization model!
- It works on the concept of Autoencoders. This approach was introduced by Richard Zhang in his paper Colorful Image Colorization. These autoencoders cleverly store the important details of a big image into a small space and then try to recreate this image in color. We penalize the autoencoder when it doesn't do a good job until it begins to get it right.
Feel free to head to our webapp and explore it for yourself.
You can check out our contributions, issues we faced and solutions we found in Contribute.md. Feel free to fork this repository and make your own contributions.
|
Abhishek Saxena
|
Aditya Shukla
|
Ansh Sharma
|
Harsh Sharma
|
MIT © Data Science Community SRM
This project is licensed under the MIT License - see the License.md file for details
Made with ❤️ by DS Community SRM