DPTE-Net: Distilled Pooling Transformer Encoder for Efficient Realistic Image Dehazing

The official implementation of the paper Distilled Pooling Transformer Encoder for Efficient Realistic Image Dehazing.

Authors: Le-Anh Tran, Dong-Chul Park

Journal: Neural Computing and Applications (Springer), 2024

Introduction

Framework diagram

Test

• Create environment & install required packages

conda env create -f environment.yaml
conda activate dpteenv2

• Download pre-trained weights from Hugging Face
• Prepare test data
• Run test

python dehaze.py

• Evaluate PSNR & SSIM

python eval_psnr_ssim.py

Train

• Create environment & install required packages
• Prepare dataset (a parent directory containing two sub-folders 'A' and 'B' like below):

.../path/to/data
            | A (containing hazy images)
            | B (containing clean images)
*** Note: a pair of hazy-clean images must have the same name

• Configure training parameters in train.py
• Train command

python train.py

Citation

Please cite our paper if you use the data in this repo.

@article{tran2024distilled,
  title={Distilled pooling transformer encoder for efficient realistic image dehazing},
  author={Tran, Le-Anh and Park, Dong-Chul},
  journal={Neural Computing and Applications},
  pages={1--19},
  year={2024},
  publisher={Springer}
}

Have fun.

LA Tran