fmr icon indicating copy to clipboard operation
fmr copied to clipboard

This repository is the implementation of our CVPR 2020 work: "Feature-metric Registration: A Fast Semi-supervised Approach for Robust Point Cloud Registration without Correspondences"

Results 9 fmr issues
Sort by recently updated
recently updated
newest added

Can I use this model for 2D point cloud?

Is there any way to register two point clouds with a different scale with this algorithm?

I can't understand why the author chose to use the vertex of CAD Model Mesh as the point cloud for the experiment, which is very different from the real point...

I successfully trained a model using: `python train.py -data modelnet` Now, I'm attempting to evaluate the trained model using: `python evaluate.py -data modelnet --pretrained=result/fmr_model.pth` I receive the following error: ```...

thanks for sharing, nice job, and how can i get the finall result on public datesets,such as 7scence. I have no ideal with the prints: ``` test, 0/57, 1.132032 test,...

Hello, Thanks for your nice works in point cloud regestrition. Can you provide a pre-trained model on the kitti dataset? Thanks very much!

Hi, Thanks for your nice works in point cloud regestrition. I am trying to use this model to obtain rigid transformation parameters, but I find out that it seems quite...

Hello, my data‘s initial pose is large, and the overlap ratio is less than 20%, can the registration be successful with this model training?Thanks!

evaluate.py only have MRSE,No rotational or translational errors.