Learning3D: A Modern Library for Deep Learning on 3D Point Clouds Data.
Documentation | Quick Start | Python | Demo
Learning3D is an open-source library that supports the development of deep learning algorithms that deal with 3D data. The Learning3D exposes a set of state of art deep neural networks in python. A modular code has been provided for further development. We welcome contributions from the open-source community.
Available Computer Vision Algorithms in Learning3D
| Sr. No. | Tasks | Algorithms |
|---|---|---|
| 1 | Classification | PointNet, DGCNN |
| 2 | Segmentation | PointNet, DGCNN |
| 3 | Reconstruction | Point Completion Network (PCN) |
| 4 | Registration | PointNetLK, PCRNet, DCP, PRNet |
| 5 | Flow Estimation | FlowNet3D |
Available Pretrained Models
- PointNet
- PCN
- PointNetLK
- PCRNet
- DCP
- PRNet
- FlowNet3D
Available Datasets
- ModelNet40
Technical Details
Supported OS
- Ubuntu 16.04
- Ubuntu 18.04
- Linux Mint
Requirements
- CUDA 10.0 or higher
- Pytorch 1.3 or higher
- Transforms3d 0.3 or higher
- Ninja
- H5py
