ECS795P Deep Learning and Computer Vision, 2023

Course Work 1: Image Super-resolution Using Deep Learning

Aim: To obtain practical knowledge and hands-on understanding of the concepts of image super-resolution, deep learning using convolutional neural networks (CNN) and peak signal-to-noise ratio (PSNR). Start: Download CW1_ECS795P.zip from the course website at http://www.eecs.qmul.ac.uk/~sgg/_ECS795P_/.

Tasks: three subtasks are involved:

1. Coding: to add your code blocks in the required sections; (40% of this CW)
2. Report: to complete the questions in report; (30% of this CW)
3. Online assessment: to answer one question and to conduct one exercise, which are randomly selected from below. It will be carried out during the lab demo session in WK10; (30% of this CW)

Platform: Python + PyTorch

1. Understanding image super-resolution

Objective: To become familiar with the image super-resolution problem setting. Questions:

1. What is the concept of image resolution?
2. What is the gray-scale or single-channel image super-resolution?
3. What is the Ground Truth image?
4. How to measure the quality of the output high-resolution images?

Exercises:

1. To read the image named butterfly_GT.bmp
2. To show the image resolution of this image
3. To convert the image from the RGB colour space into the gray-scale space (Tip: use imageio package to read image)
4. To downsample the current image by 3 times
5. To upsample the current image by 3 times with interpolation algorithm ...