https://github.com/soooda/pointnet

The coding for my final presentation of Tokyo Institute of Technology's ART.T466 3D Computer Vision
https://github.com/soooda/pointnet

point-cloud pytorch

Last synced: 9 days ago
JSON representation

The coding for my final presentation of Tokyo Institute of Technology's ART.T466 3D Computer Vision

• Host: GitHub
• URL: https://github.com/soooda/pointnet
• Owner: Soooda
• Created: 2024-01-16T02:51:16.000Z (10 months ago)
• Default Branch: master
• Last Pushed: 2024-01-30T03:33:05.000Z (10 months ago)
• Last Synced: 2024-02-14T11:31:11.226Z (9 months ago)
• Topics: point-cloud, pytorch
• Language: Python
• Homepage:
• Size: 71.5 MB
• Stars: 0
• Watchers: 2
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# PointNet

The coding for my final presentation of Tokyo Institute of Technology's ART.T466 3D Computer Vision

## Environment

```bash

$ conda create -n PointNet pip python=3.10

# Nvidia Cuda

$ conda install pytorch==1.12.1 cudatoolkit=11.3 -c pytorch

# Mac MPS

$ conda install pytorch::pytorch -c pytorch

$ pip install h5py open3d

```

## Dataset

The ModelNet40 dataset and the dataset loader are attained from [PointCloudDatasets](https://github.com/antao97/PointCloudDatasets).

Put the extracted folder `modelnet40_hdf5_2048` under `pointnet/datasets` directory.

## References

* [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://arxiv.org/abs/1612.00593)