search

haoyu94 / Coarse-to-fine-correspondences

PyTorch implementation of NeurIPS 2021 paper: "CoFiNet: Reliable Coarse-to-fine Correspondences for Robust Point Cloud Registration"
124 stars 11 forks source link

How to get the result of kitti #4

Closed ljnaaa closed 2 years ago

ljnaaa commented 2 years ago

I've test the parameters in kitti.yaml but found it can't work, then I refer to the parameter used for 3dMatch and successfully run the code,but the result of recall is only 6.1%, what should I do if I want to get a better result in kitti?

haoyu94 commented 2 years ago

Hi, thanks for your interest.

As I separately trained 3DMatch and KITTI, I first uploaded the code for 3DMatch for quick re-implementation of the whole model. I will try to add the code and pre-trained weights for KITTI later.

haoyu94 commented 2 years ago

The kitti part has been updated.