|
--- |
|
license: other |
|
|
|
tags: |
|
- diffusion |
|
- point-cloud |
|
- airplane |
|
- 3D |
|
|
|
datasets: |
|
- shapenet |
|
--- |
|
|
|
### Model Description |
|
– Luo, Shitong and Hu, Wei |
|
– 2021 |
|
|
|
Proposed a probabilistic generative model for point clouds inspired by non-equilibrium thermodynamics, exploiting the reverse diffusion process to learn the point distribution. All models are available on the original [***Github repo Link***](https://github.com/luost26/diffusion-point-cloud). It consists of a model for airplane model generating. |
|
|
|
|
|
### Documents |
|
- [GitHub Repo](https://github.com/luost26/diffusion-point-cloud) |
|
- [Paper - Diffusion Probabilistic Models for 3D Point Cloud Generation](https://arxiv.org/abs/2103.01458) |
|
|
|
### Datasets |
|
ShapeNet is a comprehensive 3D shape dataset created for research in computer graphics, computer vision, robotics and related diciplines. |
|
|
|
- [Offical Dataset of ShapeNet](https://shapenet.org/) |
|
- [author's training dataset](https://drive.google.com/drive/folders/1SRJdYDkVDU9Li5oNFVPOutJzbrW7KQ-b?usp=share_link) |
|
- [pre-trained models](https://drive.google.com/drive/folders/1sH7v2xmQ6ImC4rll28mktEK4hucFO_yz?usp=share_link) |
|
|
|
|
|
### How to use |
|
|
|
```python |
|
# Train an auto-encoder |
|
python train_ae.py |
|
|
|
# Train a generator |
|
python train_gen.py |
|
``` |
|
|
|
```python |
|
# Test an auto-encoder |
|
python test_ae.py --ckpt ./pretrained/AE_all.pt --categories all |
|
|
|
# Test a generator |
|
python test_gen.py --ckpt ./pretrained/GEN_airplane.pt --categories airplane |
|
``` |
|
|
|
### BibTeX Entry and Citation Info |
|
``` |
|
@inproceedings{luo2021diffusion, |
|
author = {Luo, Shitong and Hu, Wei}, |
|
title = {Diffusion Probabilistic Models for 3D Point Cloud Generation}, |
|
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, |
|
month = {June}, |
|
year = {2021} |
|
} |
|
``` |
