https://github.com/deeperlearner/depth-face-anti-spoofing
Project of anti-spoofing by generating depth of face.
https://github.com/deeperlearner/depth-face-anti-spoofing
computer-vision face-anti-spoofing pytorch
Last synced: 2 months ago
JSON representation
Project of anti-spoofing by generating depth of face.
- Host: GitHub
- URL: https://github.com/deeperlearner/depth-face-anti-spoofing
- Owner: deeperlearner
- Created: 2025-04-23T03:47:02.000Z (about 1 year ago)
- Default Branch: master
- Last Pushed: 2025-04-29T09:13:06.000Z (about 1 year ago)
- Last Synced: 2025-06-05T04:26:38.380Z (about 1 year ago)
- Topics: computer-vision, face-anti-spoofing, pytorch
- Language: Python
- Homepage:
- Size: 44.9 KB
- Stars: 1
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# depth-face-anti-spoofing
This project is generated by [pytorch-template](https://github.com/deeperlearner/pytorch-template).
# Dataset
# Method
The idea is that using DQNet model to predict the depth of face and use the mean of the predicted detph as output score.
By using `depth_face.sh`, we can generate the ground truth depth of real face.
And the depth of a spoof face is an all zero image.
After training DQNet for a few epochs, we add an auxiliary branch to train a binary classification to output real or spoof face.
# Reference
* The depth of real face is generated by [3DDFA_V2](https://github.com/cleardusk/3DDFA_V2).
* The DQNet structure is borrowed from [Face De-Spoofing: Anti-Spoofing via Noise Modeling](https://openaccess.thecvf.com/content_ECCV_2018/html/Yaojie_Liu_Face_De-spoofing_ECCV_2018_paper.html).