mmpose/configs/body_3d_keypoint/README.md

14 lines
736 B
Markdown

# Human Body 3D Pose Estimation
3D pose estimation is the detection and analysis of X, Y, Z coordinates of human body joints from RGB images. For single-person 3D pose estimation from a monocular camera, existing works can be classified into three categories: (1) from 2D poses to 3D poses (2D-to-3D pose lifting) (2) jointly learning 2D and 3D poses, and (3) directly regressing 3D poses from images.
## Data preparation
Please follow [DATA Preparation](/docs/en/dataset_zoo/3d_body_keypoint.md) to prepare data.
## Demo
Please follow [Demo](/demo/docs/en/3d_human_pose_demo.md) to run demos.
<img src="https://user-images.githubusercontent.com/15977946/118820606-02df2000-b8e9-11eb-9984-b9228101e780.gif" width="600px" alt><br>