Awesome

Requirements

• Python 3.6 (Anaconda is recommended)
• skimage
• imageio
• Pytorch 1.4.0
• torchvision 0.5.0
• tqdm
• pandas
• cv2 (pip install opencv-python)

Test

Prepare test data

1. Download the KITTI2012 dataset and put folders testing/colored_0 and testing/colored_1 in data/test/KITTI2012/original
2. Cd to data/test and run generate_testset.m to generate test data.
3. (optional) You can also download KITTI2015, Middlebury or other stereo datasets and prepare test data in data/test as below:

  datasets
  └── test
      ├── dataset_1
            ├── hr
                ├── scene_1
                      ├── hr0.png
                      └── hr1.png
                ├── ...
                └── scene_M
            └── lr_x4
                ├── scene_1
                      ├── lr0.png
                      └── lr1.png
                ├── ...
                └── scene_M
      ├── ...
      └── dataset_N

Demo

python cvcnet_test.py 

Train

python cvcnet_train.py