https://github.com/ofnote/3d-face
https://github.com/ofnote/3d-face
3d-face-reconstruction
Last synced: 6 months ago
JSON representation
- Host: GitHub
- URL: https://github.com/ofnote/3d-face
- Owner: ofnote
- License: apache-2.0
- Created: 2021-07-01T11:08:26.000Z (over 4 years ago)
- Default Branch: main
- Last Pushed: 2021-09-21T12:23:53.000Z (about 4 years ago)
- Last Synced: 2025-04-15T15:04:53.941Z (6 months ago)
- Topics: 3d-face-reconstruction
- Language: Python
- Homepage: https://medium.com/offnote-labs/3d-face-and-body-reconstruction-95f59ada1040
- Size: 60.6 MB
- Stars: 2
- Watchers: 2
- Forks: 3
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
## Getting Started
Clone the repo:
```bash
git clone https://github.com/ofnote/3d-face
cd 3d-face
```
### Requirements
* Python 3.7 (numpy, skimage, scipy, opencv)
* PyTorch >= 1.6 (pytorch3d)
* face-alignment (Optional for detecting face)
You can run
```bash
pip install -r requirements.txt
```
Then follow the instruction to install [pytorch3d](https://github.com/facebookresearch/pytorch3d/blob/master/INSTALL.md).
### Training
* To generate CSV file containing images paths, first specify the directory inside preprocess.py containing training images
Run
```bash
python3 -m decalib.datasets.preprocess
```
* Specify the dataset foldername inside train file in line 267.
* To start training
Run
```bash
python3 -m decalib.trainFromscratch.train
```
## Acknowledgements
- [DECA](https://github.com/yadiraF/DECA/) - Used their coarse reconstruction part for reconstructing 3d face.