Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,49 @@
|
|
1 |
---
|
2 |
license: cc-by-nc-4.0
|
3 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
license: cc-by-nc-4.0
|
3 |
+
---
|
4 |
+
|
5 |
+
# Model Card for Tailor3D
|
6 |
+
|
7 |
+
## π Overview
|
8 |
+
|
9 |
+
This model card is for the **Tailor3D** project. You can see the more information below.
|
10 |
+
- **Github Code**: [Link to Github](https://tailor3d-2024.github.io/)
|
11 |
+
- **Arxiv Paper**: [Link to Arxiv](https://tailor3d-2024.github.io/)
|
12 |
+
- **Project Page**: [Link to Project](https://tailor3d-2024.github.io/)
|
13 |
+
- **Youtube Video**: [Link to Youtube](https://tailor3d-2024.github.io/)
|
14 |
+
|
15 |
+
## ποΈ Model Details
|
16 |
+
|
17 |
+
- Pretrained Models
|
18 |
+
|
19 |
+
| Model | Pretained Model | Training Data |
|
20 |
+
| :---: | :---: | :---: |
|
21 |
+
| [tailor3d-small-1.0](https://huggingface.co/alexzyqi/tailor3d-small-1.0) | [openlrm-mix-small-1.1](https://huggingface.co/zxhezexin/openlrm-mix-small-1.1) | Objaverse + MVImgNet |
|
22 |
+
| [tailor3d-base-1.0](https://huggingface.co/alexzyqi/tailor3d-base-1.0) | [openlrm-mix-base-1.1](https://huggingface.co/zxhezexin/openlrm-mix-base-1.1) | Objaverse + MVImgNet |
|
23 |
+
| [tailor3d-large-1.0](https://huggingface.co/alexzyqi/tailor3d-large-1.0)| [openlrm-mix-large-1.1](https://huggingface.co/zxhezexin/openlrm-mix-large-1.1) | Objaverse + MVImgNet |
|
24 |
+
|
25 |
+
- Model architecture (same as [OpenLRM](https://huggingface.co/zxhezexin/openlrm-mix-large-1.1)).
|
26 |
+
|
27 |
+
| Type | Layers | Feat. Dim | Attn. Heads | Triplane Dim. | Input Res. | Image Encoder |
|
28 |
+
| :---: | :----: | :-------: | :---------: | :-----------: | :--------: | :---------------: |
|
29 |
+
| small | 12 | 512 | 8 | 32 | 224 | dinov2_vits14_reg |
|
30 |
+
| base | 12 | 768 | 12 | 48 | 336 | dinov2_vitb14_reg |
|
31 |
+
| large | 16 | 1024 | 16 | 80 | 448 | dinov2_vitb14_reg |
|
32 |
+
|
33 |
+
- Training settings (same as [OpenLRM](https://huggingface.co/zxhezexin/openlrm-mix-large-1.1)).
|
34 |
+
|
35 |
+
| Type | Rend. Res. | Rend. Patch | Ray Samples |
|
36 |
+
| :---: | :--------: | :---------: | :---------: |
|
37 |
+
| small | 192 | 64 | 96 |
|
38 |
+
| base | 288 | 96 | 96 |
|
39 |
+
| large | 384 | 128 | 128 |
|
40 |
+
|
41 |
+
## π OpenLRM as the Pretained Model
|
42 |
+
This repo, we use the LRM as the pretrained model. These are the link of its [arxiv paper](https://arxiv.org/abs/2311.04400) and [open-source implementation](https://github.com/3DTopia/OpenLRM).
|
43 |
+
|
44 |
+
All regulations are the same as the OpenLRM.
|
45 |
+
|
46 |
+
## π License
|
47 |
+
|
48 |
+
- The model weights are released under the Creative Commons Attribution-NonCommercial 4.0 International License.
|
49 |
+
- They are provided for research purposes only, and CANNOT be used commercially.
|