Image Super Resolution using Deep Neural Networks
Mentors :
Tanay Tayal
Shantanu Welling
Param Shah
Mentees :
8-10
We propose a deep learning method for single image super-resolution. They will start by learning the basics of python and then proceed onto deep learning. Following which they learn about deep neural network architecture for image super resolution and implement a model that takes a low-resolution image as the input and outputs the high-resolution one. Further readings: https://medium.com/analytics-vidhya/super-resolution-and-its-recent-advances-in-deep-learning-part-1-c6d927914d32
Prerequisites: None. Interest in image processing is appreciated. Basic knowledge about python and deep learning is a bonus but not necessary.
Tentative Timeline :
| Week | Work |
|---|---|
| Week 1 | Brushing up Python Basics |
| Week 2 | Introduction to Deep Learning |
| Week 3 | Convolutional Neural Networks using numpy |
| Week 4-5 | Building basic Deep Neural Networks |
| Week 6 | Understanding Image Super Resolution and proposing suitable architectures |
| Week 7-8 | Implementation of the model |
