Skip to content

A project to experiment advancements to image super resolution via iterative refinement.

License

Notifications You must be signed in to change notification settings

PurvaG1700/SR3_ImageSuperResolution

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

94 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Image Super-Resolution via Iterative Refinement

Paper | Project

Brief

Code Submission for UCLA CS245: Big Data Analytics course offered in Fall 2023

This is an unofficial implementation of Image Super-Resolution via Iterative Refinement(SR3) by PyTorch.

The other branches contain updated code for each specific experiments (zero_snr, splitImage, lazcos, bilinear_unet, and area-bicubic-upsampling-unet). This master branch only contains the unedited version of the unofficial code for the SR3 Paper (https://github.com/Janspiry/Image-Super-Resolution-via-Iterative-Refinement)

Please refer to each branch for advancements to SR3


## Acknowledgements

Our work is based on the following theoretical works:

- [Denoising Diffusion Probabilistic Models](https://arxiv.org/pdf/2006.11239.pdf)
- [Image Super-Resolution via Iterative Refinement](https://arxiv.org/pdf/2104.07636.pdf)
- [WaveGrad: Estimating Gradients for Waveform Generation](https://arxiv.org/abs/2009.00713)
- [Large Scale GAN Training for High Fidelity Natural Image Synthesis](https://arxiv.org/abs/1809.11096)

Furthermore, we are benefitting a lot from the following projects:

- https://github.com/bhushan23/BIG-GAN
- https://github.com/lmnt-com/wavegrad
- https://github.com/rosinality/denoising-diffusion-pytorch
- https://github.com/lucidrains/denoising-diffusion-pytorch
- https://github.com/hejingwenhejingwen/AdaFM

About

A project to experiment advancements to image super resolution via iterative refinement.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 100.0%