Update README.md
Browse filesADDED Model Description, Datasets, Documents and How to use sections
README.md
CHANGED
@@ -6,17 +6,47 @@ tags:
|
|
6 |
- point-cloud
|
7 |
- airplane
|
8 |
- 3D
|
|
|
|
|
|
|
9 |
---
|
10 |
|
11 |
-
###
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
12 |
|
13 |
-
|
14 |
|
15 |
-
|
|
|
|
|
16 |
|
17 |
-
|
|
|
|
|
18 |
|
|
|
|
|
|
|
19 |
|
|
|
|
|
|
|
20 |
|
21 |
### BibTeX Entry and Citation Info
|
22 |
```
|
|
|
6 |
- point-cloud
|
7 |
- airplane
|
8 |
- 3D
|
9 |
+
|
10 |
+
datasets:
|
11 |
+
- shapenet
|
12 |
---
|
13 |
|
14 |
+
### Model Description
|
15 |
+
– Luo, Shitong and Hu, Wei
|
16 |
+
– 2021
|
17 |
+
|
18 |
+
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.
|
19 |
+
|
20 |
+
|
21 |
+
### Documents
|
22 |
+
- [GitHub Repo](https://github.com/luost26/diffusion-point-cloud)
|
23 |
+
- [Paper - Diffusion Probabilistic Models for 3D Point Cloud Generation](https://arxiv.org/abs/2103.01458)
|
24 |
+
|
25 |
+
### Datasets
|
26 |
+
ShapeNet is a comprehensive 3D shape dataset created for research in computer graphics, computer vision, robotics and related diciplines.
|
27 |
+
|
28 |
+
- [Offical Dataset of ShapeNet](https://shapenet.org/)
|
29 |
+
- [author's training dataset](https://drive.google.com/drive/folders/1SRJdYDkVDU9Li5oNFVPOutJzbrW7KQ-b?usp=share_link)
|
30 |
+
- [pre-trained models](https://drive.google.com/drive/folders/1sH7v2xmQ6ImC4rll28mktEK4hucFO_yz?usp=share_link)
|
31 |
+
|
32 |
|
33 |
+
### How to use
|
34 |
|
35 |
+
```python
|
36 |
+
# Train an auto-encoder
|
37 |
+
python train_ae.py
|
38 |
|
39 |
+
# Train a generator
|
40 |
+
python train_gen.py
|
41 |
+
```
|
42 |
|
43 |
+
```python
|
44 |
+
# Test an auto-encoder
|
45 |
+
python test_ae.py --ckpt ./pretrained/AE_all.pt --categories all
|
46 |
|
47 |
+
# Test a generator
|
48 |
+
python test_gen.py --ckpt ./pretrained/GEN_airplane.pt --categories airplane
|
49 |
+
```
|
50 |
|
51 |
### BibTeX Entry and Citation Info
|
52 |
```
|