Skip to content
An implementation of paper "Heavy Rain Image Restoration: Integrating Physics Model and Conditional Adversarial Learning" (CVPR19)
Python MATLAB
Branch: master
Clone or download
Latest commit e92dda3 Aug 1, 2019
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
data All codes May 13, 2019
datagen Update README.md Jul 10, 2019
Base.py All codes May 13, 2019
README.md Update README.md Aug 1, 2019
helper.py All codes May 13, 2019
model.py All codes May 13, 2019
networks.py All codes May 13, 2019
test.py All codes May 13, 2019
train.py All codes May 13, 2019
unet_parts.py All codes May 13, 2019

README.md

HeavyRainRemoval

0. Installation

Framework

  1. Python 2.7
  2. Pytorch (only ubuntu 0.4.0 version is tested so far)
  3. Torchvision

Python Dependencies

  1. tqdm
  2. skimage
  3. opencv
  4. numpy
  5. DeepGuidedFilter: pip install guided-filter-pytorch

1. Demo

To run rain removal, please first download the pretrained model. Open your terminal and type:

python test.py

2. Training Dataset

You may download the synthetic Outdoor-Rain (7GB) datasets at here.

3. Train (coming soon)

please email liruoteng@gmail.com if you have any issues running this code.

You can’t perform that action at this time.