Skip to content
/ Universal-Equivariant-PointNet-like-MLPs-and-Group-Equivariant-CNNs-for-3D-Point-Clouds Public

Point cloud is a compact representation of 3D objects and is widely used by sensors like RGB-Depth camera and LiDAR. Unfortunately, due to its irregular and unordered nature, 3D point cloud is extremely challenging to work with. This work seeks to improve generalization and data efficiency of neural networks for 3D point clouds by inducing equiv…

License

MIT license
1 star 0 forks Branches Tags Activity
Star
Notifications You must be signed in to change notification settings

AlanLeAI/Universal-Equivariant-PointNet-like-MLPs-and-Group-Equivariant-CNNs-for-3D-Point-Clouds

BranchesTags

Repository files navigation

GPointConv

Installation

The code is modified from repo https://github.com/DylanWusee/pointconv_pytorch

Tensorflow version

https://github.com/kenakai16/gpointconv_tf

Usage

ModelNet40 Classification

Download the ModelNet40 dataset from here. This dataset is the same one used in PointNet, thanks to Charles Qi.

To train the model,

python train_cls_gconv.py --model gpointconv_modelnet40 --normal

To evaluate the model,

python eval_cls_gconv.py --checkpoint ./checkpoint/check_point.pth --normal

We are updating the latest weight...

License

This repository is released under MIT License (see LICENSE file for details).

Universal-Equivariant-PointNet-like-MLPs-and-Group-Equivariant-CNNs-for-3D-Point-Clouds

About

Point cloud is a compact representation of 3D objects and is widely used by sensors like RGB-Depth camera and LiDAR. Unfortunately, due to its irregular and unordered nature, 3D point cloud is extremely challenging to work with. This work seeks to improve generalization and data efficiency of neural networks for 3D point clouds by inducing equiv…

Resources

Readme

License

MIT license
Activity

Stars

1 star

Watchers

1 watching

Forks

0 forks
Report repository

Releases

No releases published

Packages

No packages published

Languages