Skip to content

Super Resolution using EDSR. Enhanced Deep Residual Networks for Single Image Super-Resolution (EDSR) model trained to convert a Low-Resolution image to a Super-Resolution image.

Notifications You must be signed in to change notification settings

aryanjain28/Super-Resolution

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

21 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Super-Resolution

Super Resolution using EDSR. Enhanced Deep Residual Networks for Single Image Super-Resolution (EDSR) model trained to convert a Low-Resolution image to a Super-Resolution image.

Process (Brief explanation)

  1. We train an EDSR model with low-resolution image as input and the same high-resolution image as output. Generator and Discriminator part is not used here.
  2. After training EDSR like above, we fine tune the high resolution (HR) images by building a model using EDSR as generator and a discriminator and train it giving LR and HR images pair as input and taking SR images as output.

Dataset

DIV2K: https://data.vision.ee.ethz.ch/cvl/DIV2K/

Model architecture



Screenshots

Things I learnt

  1. Training a super resolution model is difficult without a very powerful GPU.
  2. About EDSR, WSDR and SR-GAN models.
  3. About Perceptual loss and Pixel loss.

References

  1. This project is highly inspired by: http://krasserm.github.io/2019/09/04/super-resolution/#model-training
  2. Do check his project for depp explanation: https://github.com/krasserm/super-resolution

Note: I tried training the model on my GPU and failed miserably. Then I tried training it on Colab's GPU, and failed again. At last I had to use pre-trained weights on my model.

About

Super Resolution using EDSR. Enhanced Deep Residual Networks for Single Image Super-Resolution (EDSR) model trained to convert a Low-Resolution image to a Super-Resolution image.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages