# CoMA: Convolutional Mesh Autoencoders
![Generating 3D Faces using Convolutional Mesh Autoencoders](https://coma.is.tue.mpg.de/uploads/ckeditor/pictures/91/content_coma_faces.jpg)
This is an official repository of [Generating 3D Faces using Convolutional Mesh Autoencoders](https://coma.is.tue.mpg.de)
[[Project Page](https://coma.is.tue.mpg.de)][[Arxiv](https://arxiv.org/abs/1807.10267)]
**UPDATE :** Thank you for using and supporting this repository over the last two years. This will no longer be maintained. Alternatively, please use:
- [sw-gong/coma](https://github.com/sw-gong/coma), thanks to Shunwang Gong.
- [pixelite1201/pytorch_coma](https://github.com/pixelite1201/pytorch_coma/), thanks to Priyanka Patel.
## Requirements
This code is tested on Tensorflow 1.3. Requirements (including tensorflow) can be installed using:
```bash
pip install -r requirements.txt
```
Install mesh processing libraries from [MPI-IS/mesh](https://github.com/MPI-IS/mesh).
## Data
Download the data from the [Project Page](https://coma.is.tue.mpg.de).
Preprocess the data
```bash
python processData.py --data <PATH_OF_RAW_DATA> --save_path <PATH_TO_SAVE_PROCESSED DATA>
```
Data pre-processing creates numpy files for the interpolation experiment and extrapolation experiment (Section X of the paper).
This creates 13 different train and test files.
`sliced_[train|test]` is for the interpolation experiment.
`<EXPRESSION>_[train|test]` are for cross validation cross 12 different expression sequences.
## Training
To train, specify a name, and choose a particular train test split. For example,
```bash
python main.py --data data/sliced --name sliced
```
## Testing
To test, specify a name, and data. For example,
```bash
python main.py --data data/sliced --name sliced --mode test
```
#### Reproducing results in the paper
Run the following script. The models are slightly better (~1% on average) than ones reported in the paper.
```bash
sh generateErrors.sh
```
## Sampling
To sample faces from the latent space, specify a model and data. For example,
```bash
python main.py --data data/sliced --name sliced --mode latent
```
A face template pops up. You can then use the keys `qwertyui` to sample faces by moving forward in each of the 8 latent dimensions. Use `asdfghjk` to move backward in the latent space.
For more flexible usage, refer to [lib/visualize_latent_space.py](https://github.com/anuragranj/coma/blob/master/lib/visualize_latent_space.py).
## Acknowledgements
We thank [Raffi Enficiaud](https://www.is.mpg.de/person/renficiaud) and [Ahmed Osman](https://ps.is.tuebingen.mpg.de/person/aosman) for pushing the release of [psbody.mesh](https://github.com/MPI-IS/mesh), an essential dependency for this project.
## License
The code contained in this repository is under MIT License and is free for commercial and non-commercial purposes. The dependencies, in particular, [MPI-IS/mesh](https://github.com/MPI-IS/mesh) and our [data](https://coma.is.tue.mpg.de) have their own license terms which can be found on their respective webpages. The dependencies and data are NOT covered by MIT License associated with this repository.
## Related projects
[CAPE (CVPR 2020)](https://github.com/QianliM/CAPE): Based on CoMA, we build a conditional Mesh-VAE-GAN to learn the clothing deformation from the SMPL body model, making a generative, animatable model of people in clothing. A large-scale mesh dataset of clothed humans in motion is also included!
## When using this code, please cite
Anurag Ranjan, Timo Bolkart, Soubhik Sanyal, and Michael J. Black. "Generating 3D faces using Convolutional Mesh Autoencoders." European Conference on Computer Vision (ECCV) 2018.
没有合适的资源?快使用搜索试试~ 我知道了~
用于生成3D人脸的卷积网格自动编码器_Python_Shell_下载.zip
共66个文件
index:12个
data-00000-of-00001:12个
checkpoint:12个
1.该资源内容由用户上传,如若侵权请联系客服进行举报
2.虚拟产品一经售出概不退款(资源遇到问题,请及时私信上传者)
2.虚拟产品一经售出概不退款(资源遇到问题,请及时私信上传者)
版权申诉
0 下载量 120 浏览量
2023-04-30
23:57:46
上传
评论
收藏 13.44MB ZIP 举报
温馨提示
用于生成3D人脸的卷积网格自动编码器_Python_Shell_下载.zip
资源推荐
资源详情
资源评论
收起资源包目录
用于生成3D人脸的卷积网格自动编码器_Python_Shell_下载.zip (66个子文件)
coma-master
compareModels.py 2KB
lib
utils.py 15KB
__init__.py 0B
visualize_latent_space.py 2KB
models.py 56KB
graph.py 7KB
coarsening.py 9KB
mesh_sampling.py 8KB
processData.py 898B
main.py 5KB
data
template.obj 306KB
LICENSE 2KB
computeErrors.py 3KB
facemesh.py 8KB
requirements.txt 102B
checkpoints
eyebrow
checkpoint 81B
model-320400.index 2KB
model-320400.meta 6.02MB
model-320400.data-00000-of-00001 235KB
cheeks_in
checkpoint 81B
model-351600.meta 6.02MB
model-351600.index 2KB
model-351600.data-00000-of-00001 235KB
mouth_extreme
checkpoint 81B
model-364600.meta 6.02MB
model-364600.index 2KB
model-364600.data-00000-of-00001 235KB
lips_back
checkpoint 81B
model-350081.meta 6.02MB
model-350081.data-00000-of-00001 235KB
model-350081.index 2KB
lips_up
checkpoint 81B
model-353512.meta 6.02MB
model-353512.data-00000-of-00001 235KB
model-353512.index 2KB
mouth_open
checkpoint 81B
model-334400.data-00000-of-00001 235KB
model-334400.meta 6.02MB
model-334400.index 2KB
mouth_side
checkpoint 81B
model-344400.data-00000-of-00001 235KB
model-344400.meta 6.02MB
model-344400.index 2KB
mouth_down
checkpoint 81B
model-326400.data-00000-of-00001 235KB
model-326400.meta 6.02MB
model-326400.index 2KB
mouth_up
checkpoint 81B
model-316200.index 2KB
model-316200.data-00000-of-00001 235KB
model-316200.meta 6.02MB
high_smile
model-342200.index 2KB
checkpoint 81B
model-342200.data-00000-of-00001 235KB
model-342200.meta 6.02MB
mouth_middle
checkpoint 81B
model-341000.meta 6.02MB
model-341000.index 2KB
model-341000.data-00000-of-00001 235KB
bareteeth
checkpoint 81B
model-334800.data-00000-of-00001 235KB
model-334800.index 2KB
model-334800.meta 6.02MB
.gitignore 46B
generateErrors.sh 833B
README.md 4KB
共 66 条
- 1
资源评论
快撑死的鱼
- 粉丝: 1w+
- 资源: 9156
上传资源 快速赚钱
- 我的内容管理 展开
- 我的资源 快来上传第一个资源
- 我的收益 登录查看自己的收益
- 我的积分 登录查看自己的积分
- 我的C币 登录后查看C币余额
- 我的收藏
- 我的下载
- 下载帮助
安全验证
文档复制为VIP权益,开通VIP直接复制
信息提交成功