基于DAD-3DHeads 的特征点标记、姿态评估、头部3D对齐Demo

山河已无恙

发布于 2023-08-21 14:29:38

2000

发布于 2023-08-21 14:29:38

文章被收录于专栏：山河已无恙山河已无恙

1写在前面

工作中遇到，简单整理，博文为DAD-3DHeads 特征点标记、姿态评估、头部 3D 对齐 Demo
理解不足小伙伴帮忙指正

不被喜欢的姑娘喜欢，是一件很伤心的事情，可天没有塌下来，该怎么活，还得怎么活。——烽火戏诸侯《剑来》

2环境安装

克隆项目

https://github.com/PinataFarms/DAD-3DHeads.git

模型文件，如果不能访问国外网站，需要提前下载，放到家目录下: C:\Users\liruilong\.dad_checkpoints

dad_3dheads.trcd: https://media.pinatafarm.com/public/research/dad-3dheads/dad_3dheads.trcd

创建虚拟环境

(base) C:\Users\liruilong\Documents\GitHub>cd DAD-3DHeads_Demo

(base) C:\Users\liruilong\Documents\GitHub\DAD-3DHeads_Demo>conda create --name DAD-3DHeads python=3.8

(base) C:\Users\liruilong\Documents\GitHub\DAD-3DHeads_Demo>conda activate DAD-3DHeads

(DAD-3DHeads) C:\Users\liruilong\Documents\GitHub\DAD-3DHeads_Demo>pip install -r requirements.txt  -i http://pypi.douban.com/simple/ --trusted-host pypi.douban.com
Looking in indexes: http://pypi.douban.com/simple/

3运行 Demo 测试

68 个特征点标记,同时支持191，445 特征点标记

(DAD-3DHeads) C:\Users\liruilong\Documents\GitHub\DAD-3DHeads_Demo> python demo.py images\\demo_heads\\1.jpeg outputs 68_landmarks

面部曲面标记

(DAD-3DHeads) C:\Users\liruilong\Documents\GitHub\DAD-3DHeads_Demo> python demo.py images/demo_heads/1.jpeg outputs face_mesh

头部3D曲面标记

python demo.py images/demo_heads/1.jpeg outputs head_mesh

姿态评估

python demo.py images/demo_heads/1.jpeg outputs pose

其他的所有 Demo

python demo.py <path/to/input/image.png> <path/to/output/folder> <type_of_output>

# Visualize 68 2D face landmarks
python demo.py images/demo_heads/1.jpeg outputs 68_landmarks

# Visualize 191 2D face landmarks
python demo.py images/demo_heads/1.jpeg outputs 191_landmarks

# Visualize 445 2D face landmarks
python demo.py images/demo_heads/1.jpeg outputs 445_landmarks

# Visualize face mesh
python demo.py images/demo_heads/1.jpeg outputs face_mesh

# Visualize head mesh
python demo.py images/demo_heads/1.jpeg outputs head_mesh

# Visualize head pose
python demo.py images/demo_heads/1.jpeg outputs pose

# Get 3D mesh .obj file
python demo.py images/demo_heads/1.jpeg outputs 3d_mesh

# Get flame parameters .json file
python demo.py images/demo_heads/1.jpeg outputs flame_params