• A novel pairwise feature LSP to extract structural information, which is beneficial for accurate matching especially when the illumination of the image pair is imbalanced
• A novel disparity refinement method CSR (or DSR to save memory) to deal with outliers that are difficult to match, e.g. disparity discontinuities and occluded regions.

• Python 3.6
• PyTorch 1.7.0
• torchvision 0.3.0
• SceneFlow
• KITTI stereo 2015
• KITTI stereo 2012

python train.py --data_path (your Scene Flow data folder)

python KITTI_ft.py --data_path (your KITTI training data folder) --load_path (the path of the model trained on SceneFlow)

Google Drive