Skip to content

Latest commit

 

History

History
57 lines (44 loc) · 2.21 KB

README.md

File metadata and controls

57 lines (44 loc) · 2.21 KB
Raw

Multi-Expert Adaptive Selection: Task-Balancing for All-in-One Image Restoration

Continuously updating!

Note: Still under review, this code repository is not yet fully complete.

1.Quick Start

Install

This repository is built in PyTorch 1.12.0 and Python 3.8 Follow these intructions

  1. Clone our repository
git clone  https://github.com/zhoushen1/MEASNet
cd MEASNet
  1. Create conda environment The Conda environment used can be recreated using the env.yml file
conda env create -f env.yml

Datasets

Denoising: BSD400, WED,BSD68

Deraining: Train100L&Rain100L

Dehazing: Train RESIDE, Test SOTS-Outdoor

Deblur: GoPro

Enhance: LOL-V1

The training data should be placed in data/Train/{task_name}.

The testing data should be placed in data/test/{task_name}.

2.Training

After preparing the training data in data/ directory, use

python train.py

3.Testing

After preparing the testing data in test/ directory, use

python test.py

Results

You can download visual results from (Link：https://pan.baidu.com/s/1GHmqP9himlZ_yo9h2AYCCQ?pwd=o2kp code：o2kp)

Contact:

Don't hesitate to contact me if you meet any problems when using this code.
Zhou Shen
Faculty of Information Engineering and Automation Kunming University of Science and Technology                                                           
Email: [email protected]

Thanks

  • See More Details: Efficient Image Super-Resolution by Experts Mining, ICML 2024. Paper | Code