SMU Research Data Repository (RDR)
4 files

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

posted on 2023-10-09, 08:12 authored by Yu GUO, Yuan GAO, Ryan Wen LIU, Yuxu LU, Jingxiang QU, Shengfeng HeShengfeng He, Wenqi REN

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).


  • Python 3.7
  • Pytorch 1.9.1

Network Architecture


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


  • Place the pre-training weight in the checkpoint folder.
  • Place test hazy images in the input folder.
  • Modify the weight name in the
parser.add_argument("--model_name", type=str, default='Gmodel_40', help='model name')
  • Run
  • 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).


Confidential or personally identifiable information

  • I confirm that the uploaded data has no confidential or personally identifiable information.