Skip to content
/ UnifyFormer Public

UnifyFormer [NTIRE 2024 Blind Compressed Image Enhancement Challenge]

License

Apache-2.0 license
2 stars 0 forks Branches Tags Activity
Star
Notifications You must be signed in to change notification settings

yasharora102/UnifyFormer

BranchesTags

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

9 Commits
LICENSE
LICENSE
 
 
README.md
README.md
 
 
test.py
test.py
 
 
unifyformer_arch.py
unifyformer_arch.py
 
 

Repository files navigation

NTIRE 2024 Workshop and Challenge @ CVPR 2024

Blind Compressed Image Enhancement Challenge [3rd Position]

UnifyFormer: Unifying Group Dynamics with Channel Attention for Blind Compressed Image Enhancement

UnifyFormer_arch

Introduction

This repository is implemented for NTIRE2024 Blind Compressed Image Enhancement Challenge

By Titans Members: Yash Arora, Aditya Arora

The code is tested under Ubuntu 18.04 environment with NVIDIA A100 GPU and PyTorch 1.12.1 Python 3.10 Cuda 11.3

Clone the repository

git clone https://github.com/yasharora102/UnifyFormer.git
cd UnifyFormer

Download the pretrained model and place it in the root of the folder

wget https://github.com/yasharora102/UnifyFormer/releases/download/Weights/model_unifyformer.pth

Running the code

  • For inference on DIV2K val set, run
python test.py --tile 400 --tile_overlap 32 --self_ensemble True

About

UnifyFormer [NTIRE 2024 Blind Compressed Image Enhancement Challenge]

Resources

Readme

License

Apache-2.0 license
Activity

Stars

2 stars

Watchers

2 watching

Forks

0 forks
Report repository

Releases 1

Pretrained Model Latest
Mar 26, 2024

Packages

No packages published

Languages