Skip to content

PyTorch Wrapper for Earth-Mover-Distance (EMD) for 3D point cloud regression

Notifications You must be signed in to change notification settings

SPTAU/PyTorch2EMD

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

7 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

PyTorch Wrapper for Point-cloud Earth-Mover-Distance (EMD)

Dependency

The code has been tested on Ubuntu 22.04, PyTorch 2.0.0, CUDA 11.2.

Usage

import torch
from cuda.emd import earth_mover_distance

emdLoss = earth_mover_distance()
points1 = torch.rand(32, 1000, 3).cuda()
points2 = torch.rand(32, 2000, 3, requires_grad=True).cuda()
dist = emdLoss(points1, points2)

Author

The cuda code is originally written by Haoqiang Fan. The PyTorch wrapper is written by Kaichun Mo. Also, Jiayuan Gu provided helps.

License

MIT

About

PyTorch Wrapper for Earth-Mover-Distance (EMD) for 3D point cloud regression

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Cuda 70.7%
  • Python 24.8%
  • C++ 4.5%