ShengAo

Hi, @qsisi, thanks for your interest in our work! 1. You only need to modify these two lines of code to run on multiple GPUs: https://github.com/QingyongHu/SpinNet/blob/5581e7d184bc3b4d525d5b5e58777ea04dfdc9ab/ThreeDMatch/Train/train.py#L3 https://github.com/QingyongHu/SpinNet/blob/5581e7d184bc3b4d525d5b5e58777ea04dfdc9ab/ThreeDMatch/Train/trainer.py#L34 2. We randomly...

Hi, @Codefmeister, thanks for your interest in our work! 1. In the **Spherical Voxelization** of Section 3.2, is defined as the number of points in each voxel. 2. Each voxel...

Hi, @QWTforGithub, thanks for your interest in our work! You should use `cat proc.tar.gz* > proc.tar.gz` to synthesize each sub-volume compressed package into a `proc.tar.gz` file, and then unpack the...

Hi, @QWTforGithub The results have been provided in #8 . best, Sheng

Hi, @Gilgamesh666666, thanks for your interest in our work! The reformulation step just stores the points in the spherical voxel into the corresponding cylindrical voxel, and the coordinates of the...

Hi, @JarintotionDin, thanks for your interest in our work! In all experiments, we randomly select a set of points for feature description. Of course, you can first extract a set...

Hi, @rui2016, thanks for your interest in our work! You can try to reduce the `step_size` in `preparation.py` appropriately according to the GPU memory usage. https://github.com/QingyongHu/SpinNet/blob/5581e7d184bc3b4d525d5b5e58777ea04dfdc9ab/ThreeDMatch/Test/preparation.py#L97 For the current version,...

Hi, @majbos, thanks for your interest in our work! I uploaded a small KITTI test set in https://drive.google.com/drive/folders/19fztoJCWj7_V1HYb5UVPyD-bHvB2_XPc?usp=sharing. Maybe you need to modify the test_kitti.txt in https://github.com/QingyongHu/SpinNet/blob/main/KITTI/Test/test_kitti.txt by deleting 9...

Hi, @wyaimyj , thanks for your interest in our work! If you don't have the ground-truth transformation between two point clouds, maybe you can choose an unsupervised/self-supervised training strategy such...