/RepSurf

[CVPR 2022 Oral] Official implementation for "Surface Representation for Point Clouds"

Primary LanguagePythonApache License 2.0Apache-2.0

RepSurf - Surface Representation for Point Clouds
[CVPR 2022 Oral]

By Haoxi Ran* , Jun Liu, Chengjie Wang ( * : corresponding contact)

PWC
PWC
PWC
PWC
PWC
PWC

The pytorch official implementation of "Surface Representation for Point Clouds"

PDF | arXiv

News:

  • (Sep 10 NEW 🔥) We have uploaded the implementation of RepSurf on S3DIS along with its training log and pretrained weights.
  • (June 24 🔥) We sucessfully finished our Oral presentation at CVPR 2022!
  • (May 11) We have uploaded the implementation of RepSurf on ScanObjectNN along with its training log and pretrained weights.

Tasks:

We conduct experiments of different tasks on different codebases:

Classification: 3D Object Classification
Segmentation: 3D Semantic Segmentation

Visualization

We provide several visualization results in the folder ./visualization for a closer look at the construction of RepSurf.

License

RepSurf is under the Apache-2.0 license. Please contact the primary author Haoxi Ran (ranhaoxi@gmail.com) for commercial use.