This repository is a tensorflow implementation for
Liu, Weiquan, Xuelun Shen, Cheng Wang, Zhihong Zhang, Chenglu Wen, and Jonathan Li. "H-Net: Neural Network for Cross-domain Image Patch Matching." In IJCAI, pp. 856-863. 2018.
If you use this code in your research, please cite the paper.
This code is based on Python3 and tensorflow with CUDA 9.0.
- Download the Pretrained model.
- Extract them to the current folder so that they fall under
model
for example.
There are 160 pair full size images for training. You can process it as you wish.
Download test data and extract it. (Remember to change the data_base_path
in file trainHNet.py
)