Skip to content

This repository stores scripts used to run COMASure and its extensions. The models are studied as part of the requirements for the MSc Data Science and Machine Learning dissertation at UCL.

Notifications You must be signed in to change notification settings

ruyanshou/comasure

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

17 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

COMASure - Coordinate Network and MAML based Super-Resolution Network

This repository stores scripts used to run COMASure and its extensions. The models are studied as part of the requirements for the MSc Data Science and Machine Learning dissertation at UCL.

Disclaimers: All the implementations in this repository are made for research exploration and educational purposes only. They are not ready for industrial usages and the effectiveness is not guaranteed. In addition, permission should be obtained from the author before any distribution or reproduction.

Single Domain

Example: Image 010836 of CelebA
Bicubic: PSNR 23.2, SSIM 0.780
Meta Initialization: PSNR 23.4, SSIM 0.785
010836

Cross-Domain

Example: Image 0808 of DIV2K
Bicubic: PSNR 21.0, SSIM 0.479
Meta Initialization: PSNR 21.2, SSIM 0.494
0808

Code References

CoCoNet: https://github.com/paulbricman/python-fuse-coconet
CoCoNet+MAML: https://github.com/tancik/learnit
Fourier Feature Transformation: https://github.com/tancik/fourier-feature-networks
GAN: https://github.com/eriklindernoren/PyTorch-GAN
MAML: https://github.com/cbfinn/maml
SIREN Layer: https://colab.research.google.com/github/vsitzmann/siren/blob/master/explore_siren.ipynb

Other References

Please refer to the actual report.

About

This repository stores scripts used to run COMASure and its extensions. The models are studied as part of the requirements for the MSc Data Science and Machine Learning dissertation at UCL.

Topics

Resources

Stars

Watchers

Forks