Skip to content

The implementation of our paper "Image Super-Resolution using Aggregated Residual Transformation Networks with Spatial Attention ".

License

Notifications You must be signed in to change notification settings

Xingrun-Xing/ARAN

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

22 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Aggregated Residual Attention Network (ARAN)

This is the implementation of our paper "Image Super-Resolution using Aggregated Residual Transformation Networks with Spatial Attention ". We provide the architectures and pretrained models as above. This readme is updating now, and if you need more detailed information, please contact me at [email protected] or [email protected].

Run(the same as WDSR)

Requirements:

  • Install PyTorch (tested on release 0.4.0 and 0.4.1).
  • Clone EDSR-Pytorch as backbone training framework.

Training and Validation:

  • Copy aran_cx_sx.py, into EDSR-PyTorch/src/model/.
  • Modify EDSR-PyTorch/src/option.py and EDSR-PyTorch/src/demo.sh to support --[r,g,b]_mean option (please find reference in issue #7 in the WDSR issues).
  • Launch training with EDSR-Pytorch as backbone training framework.

Results

About

The implementation of our paper "Image Super-Resolution using Aggregated Residual Transformation Networks with Spatial Attention ".

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages