/R3FA

3D Face Alignment

Primary LanguagePythonApache License 2.0Apache-2.0

Robust 3D Face Alignment with Efficient Fully Convolutional Neural Networks - Pytorch

Accepted in: The 10th International Conference on Image and Graphics(ICIG2019)-Oral

Note

In 'Demo.py' file, you will find how to run these codes. In 'FaceSwap/Demo2.py' file, you will find how to run face swap code.

Abstract

In this paper proposes a novel and efficient end-to-end 3D face alignment framework.We build an efficient and stable network model through Depthwise Separable Convolution and Densely Connected Convolutional,named MobDenseNet. Simultaneously,different loss functions are used to constrain 3D parameters based on 3D Morphable Model (3DMM) and 3D vertices

The framework of ours proposes method

MobDenseNet Structure

Layer3 Structure-DenseBlock

Experimental results

Comparison on other method

Comparison on different network structures

3D Face Alignment Results

If you have any question about this code, feel free to reach me(ljiang_jnu@outlook.com)

Citation