Image Super-Resolution
In this project we learn how to train a super-resolution model ESPCN on DIV2K dataset to upscale images using AI by 3x
super-resolution deep-learning computer-vision machine-learning artificial-general-intelligence tutorial research article

Deep learning techniques have been fairly successful in solving the problem of image and video super-resolution. In this project we will discuss the theory involved, various techniques used, loss functions, metrics, and relevant datasets. You can run the code for one of the models we'll cover, ESPCN for free on the ML Showcase.

There are many methods used to solve this task. We will cover the following:

  • Pre-Upsampling Super Resolution
  • Post-Upsampling Super Resolution
  • Residual Networks
  • Multi-Stage Residual Networks
  • Recursive Networks
  • Progressive Reconstruction Networks
  • Multi-Branch Networks
  • Attention-Based Networks
  • Generative Models We'll look at several example algorithms for each.

The content of the article is available at

Don't forget to tag @Anil-matcha in your comment, otherwise they may not be notified.

Authors original post
Co-Founder @ Vadoo backed by JioGenNext, Ef | Ex-Samsung | IIT Delhi | Author at Paperspace
Share this project
Similar projects
Deep Tutorials for PyTorch
This is a series of in-depth tutorials I'm writing for implementing cool deep learning models on your own with the amazing PyTorch library.
Second-order Attention Network for Single Image Super-resolution
We propose a second-order attention network (SAN) for more powerful feature expression and feature correlation learning.
HighRes-net: Multi-Frame Super-Resolution of satellite imagery
Pytorch implementation of HighRes-net, a neural network for multi-frame super-resolution, trained and tested on the European Space Agency’s Kelvin ...
Deep Learning Based Super Resolution, Without Using a GAN
Techniques and training a deep learning model for image improvement, image restoration, inpainting and super resolution.