tranleanh / edn-gtm

EDN-GTM for Single Image Dehazing
MIT License
33 stars 6 forks source link
convolutional-neural-networks deep-learning edn-gtm generative-adversarial-network haze-removal image-dehazing object-detection tensorflow u-net yolov4

EDN-GTM: Encoder-Decoder Network with Guided Transmission Map

Models Blog Paper Paper

The official implementation of the paper "Encoder-Decoder Networks with Guided Transmission Map for Effective Image Dehazing".

Authors: Le-Anh Tran, Dong-Chul Park

Journal: The Visual Computer (Springer), 2024

Introduction

Network Architecture:

Requirements

Main dependencies (or equivalent):

For other packages, simply run:

$ pip install -r requirements.txt

Test using Pre-trained Weights

Step 1: Download Pre-trained Weights

Step 2: Correct Data Paths in test_on_images.py

Step 3: Run Test Script

$ python test_on_images.py

Train

Step 1: Prepare Dataset

Step 2: Correct Data Paths in train.py

-- path/to/data /
                |- A (containing hazy images)
                |- B (containing clean images)

Step 3: Run Train Script

$ python train.py

Results

Quantitative results

SSIM-Speed charts

Visual results

Results on I-HAZE & O-HAZE Datasets

Results on Dense-HAZE & NH-HAZE Datasets

Results on SOTS-Outdoor & HSTS Datasets

Application to Object Detection

Dehazing in Driving Scenes

Visual dehazing results on synthetic hazy scenes:

Visual dehazing results on realistic hazy scenes:

Object Detection

(Red: ground-truth, Green: detection)

Visual dehazing + detection results on synthetic hazy scenes:

Visual dehazing + detection results on realistic hazy scenes:

Citation

@article{tran2022novel,
  title={A novel encoder-decoder network with guided transmission map for single image dehazing},
  author={Tran, Le-Anh and Moon, Seokyong and Park, Dong-Chul},
  journal={Procedia Computer Science},
  volume={204},
  pages={682--689},
  year={2022},
  publisher={Elsevier}
}

@article{tran2024encoder,
  title={Encoder-decoder networks with guided transmission map for effective image dehazing},
  author={Tran, Le-Anh and Park, Dong-Chul},
  journal={The Visual Computer},
  pages={1--24},
  year={2024},
  publisher={Springer}
}

Have fun!

LA Tran