Update README.md
Browse files
README.md
CHANGED
@@ -1,15 +1,22 @@
|
|
1 |
---
|
2 |
library_name: pytorch
|
|
|
3 |
tags:
|
4 |
- image-to-image
|
5 |
---
|
6 |
|
7 |
# ROME: Realistic one-shot mesh-based head avatars
|
8 |
-
|
9 |
|
10 |
-
|
11 |
|
12 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
13 |
```
|
14 |
@inproceedings{Khakhulin2022ROME,
|
15 |
author = {Khakhulin, Taras and Sklyarova, Vanessa and Lempitsky, Victor and Zakharov, Egor},
|
|
|
1 |
---
|
2 |
library_name: pytorch
|
3 |
+
language: en
|
4 |
tags:
|
5 |
- image-to-image
|
6 |
---
|
7 |
|
8 |
# ROME: Realistic one-shot mesh-based head avatars
|
9 |
+
[Paper](https://arxiv.org/abs/2206.08343) | [Project Page](https://samsunglabs.github.io/rome) | [Github](https://github.com/SamsungLabs/rome)
|
10 |
|
11 |
+
## Model Description
|
12 |
|
13 |
+
The ROME models can be used to create a personal avatar from a single image. The resulted meshes can be animated and rendered with photorealistic quality.
|
14 |
+
To render a ROME avatar with pretrained weights the FLAME Model and DECA weights are required.
|
15 |
+
|
16 |
+
FLAME Project: https://flame.is.tue.mpg.de/modellicense.html
|
17 |
+
|
18 |
+
|
19 |
+
## Citations
|
20 |
```
|
21 |
@inproceedings{Khakhulin2022ROME,
|
22 |
author = {Khakhulin, Taras and Sklyarova, Vanessa and Lempitsky, Victor and Zakharov, Egor},
|