Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/willyfh/farl-face-segmentation
A face segmentation implementation of FarRL model (CVPR 2022) using Facer, a face analysis toolkit for modern research.
https://github.com/willyfh/farl-face-segmentation
artificial-intelligence computer-vision deep-learning face-analysis face-parsing face-segmentation facer farl maching-learning
Last synced: 5 days ago
JSON representation
A face segmentation implementation of FarRL model (CVPR 2022) using Facer, a face analysis toolkit for modern research.
- Host: GitHub
- URL: https://github.com/willyfh/farl-face-segmentation
- Owner: willyfh
- License: mit
- Created: 2023-01-10T04:40:22.000Z (almost 2 years ago)
- Default Branch: main
- Last Pushed: 2023-12-02T15:58:14.000Z (11 months ago)
- Last Synced: 2023-12-02T16:35:43.263Z (11 months ago)
- Topics: artificial-intelligence, computer-vision, deep-learning, face-analysis, face-parsing, face-segmentation, facer, farl, maching-learning
- Language: Python
- Homepage: https://openaccess.thecvf.com/content/CVPR2022/papers/Zheng_General_Facial_Representation_Learning_in_a_Visual-Linguistic_Manner_CVPR_2022_paper.pdf
- Size: 149 KB
- Stars: 1
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE.txt
Awesome Lists containing this project
README
# Face Segmentation of FaRL Model using Facer
A face segmentation implementation of [FarRL](https://openaccess.thecvf.com/content/CVPR2022/papers/Zheng_General_Facial_Representation_Learning_in_a_Visual-Linguistic_Manner_CVPR_2022_paper.pdf) model (CVPR 2022) using [Facer](https://github.com/FacePerceiver/facer), a face analysis toolkit for modern research.
The author of FaRL performed pre-training on [LAION-FACE](https://github.com/FacePerceiver/LAION-Face), a dataset containing a large amount of face image-text pairs. They then used the pretrained encoder, to extract the image features for training a downstream task, which also includes Face Parsing task. In this work, I utilize the FaRL model which was pretrained on the Face Parsing task, and then map the predicted labels (eyes, nose, mouth, etc.) into two separate labels, i.e., face and background.
## Illustration of the FaRL Pretraining Framework
## Installation
```
conda create --name {name_env} python==3.8
conda activate {name_env}
pip install git+https://github.com/FacePerceiver/facer.git@main
pip install timm
pip install imutils
```
## Usage
```
python face_segmentation.py --image_path sample/Shin-Eun-Soo.jpg
```
To display the list of available arguments:
```
python face_segmentation.py --help
```
## Output
For left to right: segmented face image, extracted face mask, cropped face
