Data and codes for "SCANet: Self-paced semi-curricular attention network for non-homogeneous image dehazing"

This record contains the data and codes for the paper "SCANet: Self-Paced Semi-Curricular Attention Network for Non-Homogeneous Image Dehazing" published in 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

Requirement

• Python 3.7
• Pytorch 1.9.1

Network Architecture

Train

• Place the training and test image pairs in the data folder.
• Run data/makedataset.py to generate the NH-Haze20-21-23.h5 file.
• Run train.py to start training.

Test

• Place the pre-training weight in the checkpoint folder.
• Place test hazy images in the input folder.
• Modify the weight name in the test.py.
  

parser.add_argument("--model_name", type=str, default='Gmodel_40', help='model name')

• Run test.py
• The results is saved in output folder.

Pre-training Weight Download

• The weight40 Gmodel_40.tar for the NTIRE2023 val/test datasets, i.e., the weight used in the NTIRE2023 challenge.
• The weight105 Gmodel_105.tar for the NTIRE2020/2021/2023 datasets.
• The weight120 Gmodel_120.tar for the NTIRE2020/2021/2023 datasets (Add the 15 tested images as the training dataset).