DECA: Detailed Expression Capture and Animation (SIGGRAPH2021)

<img src="TestSamples/teaser/results/teaser.gif"> input image, aligned reconstruction, animation with various poses & expressions

This is the official Pytorch implementation of DECA.

DECA reconstructs a 3D head model with detailed facial geometry from a single input image. The resulting 3D head model can be easily animated. Please refer to the arXiv paper for more details.

The main features:

Reconstruction: produces head pose, shape, detailed face geometry, and lighting information from a single image.
Animation: animate the face with realistic wrinkle deformations.
Robustness: tested on facial images in unconstrained conditions. Our method is robust to various poses, illuminations and occlusions.
Accurate: state-of-the-art 3D face shape reconstruction on the NoW Challenge benchmark dataset.

Getting Started

Clone the repo:

bash
git clone https://github.com/YadiraF/DECA
cd DECA

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
```
Or use virtual environment by runing
```
bash
bash install_conda.sh
```
For visualization, we use our rasterizer that uses pytorch JIT Compiling Extensions. If there occurs a compiling error, you can install pytorch3d instead and set --rasterizer_type=pytorch3d when running the demos.

Usage

Prepare data
run script:
```
bash
bash fetch_data.sh
```

(Optional for Albedo)
follow the instructions for the Albedo model to get 'FLAME_albedo_from_BFM.npz', put it into ./data
Run demos
a. reconstruction
```
bash
python demos/demo_reconstruct.py -i TestSamples/examples --saveDepth True --saveObj True
```
to visualize the predicted 2D landmanks, 3D landmarks (red means non-visible points), coarse geometry, detailed geometry, and depth.
 <img src="Doc/images/id04657-PPHljWCZ53c-000565_inputs_inputs_vis.jpg"> <img src="Doc/images/IMG_0392_inputs_vis.jpg"> You can also generate an obj file (which can be opened with Meshlab) that includes extracted texture from the input image.
Please run python demos/demo_reconstruct.py --help for more details.

b. expression transfer
```
bash
python demos/demo_transfer.py
```
Given an image, you can reconstruct its 3D face, then animate it by tranfering expressions from other images.
Using Meshlab to open the detailed mesh obj file, you can see something like that:
 <img src="Doc/images/soubhik.gif"> (Thank Soubhik for allowing me to use his face ^_^)
Note that, you need to set '--useTex True' to get full texture.

c. for the teaser gif (reposing and animation)
```
bash
python demos/demo_teaser.py 
```
More demos and training code coming soon.

Evaluation

DECA (ours) achieves 9% lower mean shape reconstruction error on the NoW Challenge dataset compared to the previous state-of-the-art method.
The left figure compares the cumulative error of our approach and other recent methods (RingNet and Deng et al. have nearly identitical performance, so their curves overlap each other). Here we use point-to-surface distance as the error metric, following the NoW Challenge.

For more details of the evaluation, please check our arXiv paper.

Training

Prepare Training Data

a. Download image data
In DECA, we use VGGFace2, BUPT-Balancedface and VoxCeleb2

b. Prepare label
FAN to predict 68 2D landmark
face_segmentation to get skin mask

c. Modify dataloader
Dataloaders for different datasets are in decalib/datasets, use the right path for prepared images and labels.
Download face recognition trained model
We use the model from VGGFace2-pytorch for calculating identity loss,
download resnet50_ft,
and put it into ./data

Start training

Train from scratch:

bash
python main_train.py --cfg configs/release_version/deca_pretrain.yml 
python main_train.py --cfg configs/release_version/deca_coarse.yml 
python main_train.py --cfg configs/release_version/deca_detail.yml

In the yml files, write the right path for 'output_dir' and 'pretrained_modelpath'.
You can also use released model as pretrained model, then ignor the pretrain step.

for better emotion prediction: EMOCA
for better skin estimation: TRUST

Citation

If you find our work useful to your research, please consider citing:

@inproceedings{DECA:Siggraph2021,
  title={Learning an Animatable Detailed {3D} Face Model from In-The-Wild Images},
  author={Feng, Yao and Feng, Haiwen and Black, Michael J. and Bolkart, Timo},
  journal = {ACM Transactions on Graphics, (Proc. SIGGRAPH)}, 
  volume = {40}, 
  number = {8}, 
  year = {2021}, 
  url = {https://doi.org/10.1145/3450626.3459936} 
}

License

This code and model are available for non-commercial scientific research purposes as defined in the LICENSE file.
By downloading and using the code and model you agree to the terms in the LICENSE.

Acknowledgements

For functions or scripts that are based on external sources, we acknowledge the origin individually in each file.
Here are some great resources we benefit:

FLAME_PyTorch and TF_FLAME for the FLAME model
Pytorch3D, neural_renderer, SoftRas for rendering
kornia for image/rotation processing
face-alignment for cropping
FAN for landmark detection
face_segmentation for skin mask
VGGFace2-pytorch for identity loss

We would also like to thank other recent public 3D face reconstruction works that allow us to easily perform quantitative and qualitative comparisons :)
RingNet,
Deep3DFaceReconstruction,
Nonlinear_Face_3DMM,
3DDFA-v2,
extreme_3d_faces,
facescape