guobaoxiao / PGFNet

PGFNet: Preference-Guided Filtering Network for Two-View Correspondence Learning

PGFNet

PGFNet: Preference-Guided Filtering Network for Two-View Correspondence Learning

PGFNet implementation

Pytorch implementation of PGFNet

Requirements

Please use Python 3.6, opencv-contrib-python (3.4.0.12) and Pytorch (>= 1.1.0). Other dependencies should be easily installed through pip or conda.

Explanation

If you need YFCC100M and SUN3D datasets, You can visit the code at https://github.com/zjhthu/OANet.git. We have uploaded the main code on 'core' folder.

Citing PGFNet

If you find the PGFNet code useful, please consider citing:

@article{liu2023pgflnet,
  author    = {Xin Liu, Guobao Xiao*, Riqing Chen and Jiayi Ma},
  title     = {PGFNet: Preference-Guided Filtering Network for Two-View Correspondence Learning},
  booktitle = {IEEE Transactions on Image Processing (TIP)},
  year      = {2023},
  volume= {32},
  pages     = {1367-1378}
}