This project implements the AOD-Net : All-in-One Network for Dehazing for image dehazing using Python and PyTorch. The model is capable of removing haze, smoke, and water impurities from images."

The repository includes:

• Source code of AOD-Net
• Building code for synthesized hazy images based on NYU Depth V2
• Training code for our hazy dataset
• Pre-trained model for AOD-Net

Python 3.6, Pytorch 0.4.0 and other common packages

To build synthetic hazy dataset, you'll also need:

• Download NYU Depth V2 labeled dataset

1. Clone this repository
2. Create dataset from the repository root directory

   $ cd make_dataset
   $ python create_train.py --nyu {Your NYU Depth V2 path} --dataset {Your trainset path}

3. Random pick 3,169 pictures as validation set

   $ python random_select.py --traindir {Your trainset path} --valdir {Your valset path}

4. training AOD-Net

   $ python train.py --dataroot {Your trainset path} --valDataroot {Your valset path} --cuda

5. test hazy image on AOD-Net

   $ python test.py --input_image /test/canyon1.jpg  --model /model_pretrained/AOD_net_epoch_relu_10.pth --output_filename /result/canyon1_dehaze.jpg --cuda