CGFNet

Wang, Q., Xing, H., Ying, Y., & Zhou, M. (2023). CGFNet: 3D Convolution Guided and Multi-scale Volume Fusion Network for fast and robust stereo matching. Pattern Recognition Letters.

Datasets：

Scene Flow

KITTI 2012 and KITTI 2015

Middlebury

ETH3D

Network Architecture:

Benchmark Results:

Acknowledgements:

Part of the code is adopted from the related studies: BGNet, ACVNet, and GwcNet.

We would like to thank the original authors for their awesome contributions.

To cite this paper:

@article{wang2023cgfnet,
  title={CGFNet: 3D Convolution Guided and Multi-scale Volume Fusion Network for fast and robust stereo matching},
  author={Wang, Qingyu and Xing, Hao and Ying, Yibin and Zhou, Mingchuan},
  journal={Pattern Recognition Letters},
  year={2023},
  publisher={Elsevier}
}