https://github.com/anshulpaigwar/Pointwise-Convolutional-Neural-Network

PyTorch implementation of Pointwise Convolutional Neural Networks in CVPR 2018.
https://github.com/anshulpaigwar/Pointwise-Convolutional-Neural-Network

3d object-detection point-cloud pointwise pytorch pytorch-implementation

Last synced: about 2 months ago
JSON representation

PyTorch implementation of Pointwise Convolutional Neural Networks in CVPR 2018.

• Host: GitHub
• URL: https://github.com/anshulpaigwar/Pointwise-Convolutional-Neural-Network
• Owner: anshulpaigwar
• Created: 2019-06-05T13:28:53.000Z (almost 6 years ago)
• Default Branch: master
• Last Pushed: 2019-08-04T10:01:21.000Z (almost 6 years ago)
• Last Synced: 2024-10-28T07:42:45.089Z (6 months ago)
• Topics: 3d, object-detection, point-cloud, pointwise, pytorch, pytorch-implementation
• Language: Python
• Homepage:
• Size: 2.85 MB
• Stars: 12
• Watchers: 2
• Forks: 1
• Open Issues: 2
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
## PyTorch implementation of Pointwise Convolutional Neural Networks

This is unofficial PyTorch implementation of [Pointwise Convolutional Neural Networks](https://arxiv.org/pdf/1712.05245.pdf) in CVPR 2018.

Official project page for this work can be found [here](http://www.saikit.org/projects/sceneNN/home/cvpr18/index.html).

## Installation

We have tested the algorithm on the system with Ubuntu 16.04, 8 GB RAM

and NVIDIA GTX-1080.

### Dependencies

```

Python 2.7

CUDA 9.1

PyTorch 1.0

scipy

shapely

```

### Visualization

For visualization of the output bounding boxes and easy integration

with our real system we use the Robot Operating System (ROS):

```

ROS

PCL

```

## Implementation



## Training Data



## Usages