RobustMat

(IEEE TIP paper) RobustMat: Neural Diffusion for Street Landmark Patch Matching under Challenging Environments

• RobustMat and Street Landmark Patch Datasets Including:
  1. Code for RobustMat.
  2. Street Landmark Patches from KITTI Dataset and Oxford Dataset.

• Requirments

PyTorch installation:

pip install torch==1.11.0+cu113 torchvision==0.12.0+cu113 torchaudio==0.11.0

You can also use the following:

conda install pytorch==1.11.0 torchvision==0.12.0 torchaudio==0.11.0 cudatoolkit=11.3 -c pytorch

• Platform：

Ubuntu 20.04
CUDA 11.3
python 3.8

• Dataset:

Our datasets are based on three open-source datasets, including KITTI Dataset, Oxford Radar RobotCar Dataset, and Boreas Dataset

• Citation：

@article{she2023robustmat,
  title={RobustMat: Neural Diffusion for Street Landmark Patch Matching under Challenging Environments},
  author={She, Rui and Kang, Qiyu and Wang, Sijie and Y{\'a}ng, Yu{\'a}n-Ru{\`\i} and Zhao, Kai and Song, Yang and Tay, Wee Peng},
  journal={IEEE Transactions on Image Processing},
  year={2023},
  publisher={IEEE}
}