MSN-Point-Cloud-Completion icon indicating copy to clipboard operation
MSN-Point-Cloud-Completion copied to clipboard

Published 20 hours ago • verified publisher icon Colin97

Time for computing EMD

Open PenPen-ThuSilence opened this issue 4 years ago • 4 comments

Thanks for your nice implementation.

I was very confused by the running time for computing EMD. When eps = 0.05, k = 1000, I got the following results. The size of input is (32, 16834, 3).

  1. for the test_emd(), two sets of point cloud are generated randomly. Runtime is 3.57s and EMD is 0.037.
  2. however, when computing the distance between real lidar point cloud and biased real lidar point cloud, runtime is 47s and EMD is 0.182. The input pc has been normalized to [0, 1].

The runtime is much longer with real data and could you please explain the difference?

PenPen-ThuSilence avatar Feb 20 '20 02:02 PenPen-ThuSilence

Would you mind providing a pair of point clouds for me to look into the details?

Colin97 avatar Feb 20 '20 20:02 Colin97

Would you mind providing a pair of point clouds for me to look into the details?

Hello, can you please reply on https://github.com/Colin97/MSN-Point-Cloud-Completion/issues/6

levtelyatnikov avatar Mar 13 '21 11:03 levtelyatnikov

runtime is 47s for point cloud which size is (32, 16834, 3) it's same with me

zichang06 avatar Aug 28 '21 14:08 zichang06

I think you may try a smaller k.

Could you provide the example point clouds for me to take a look?

Colin97 avatar Feb 08 '22 18:02 Colin97