MediaPipe-Pose: Pose Estimation
MediaPipe Pose is a real-time human pose estimation model developed by Google, based on deep learning. The model captures and tracks 33 key points of the human body, including the head, torso, and limbs, using a single RGB camera. MediaPipe Pose employs a two-stage architecture: first, it detects the general pose region, and then a regression model accurately estimates the position of each key point. This model is efficient, accurate, and operates in real-time, making it suitable for mobile and edge devices. It is widely used in fitness tracking, motion recognition, virtual reality, and augmented reality, providing a high-quality pose estimation and tracking experience.
Source model
- Input shape: [1x3x128x128], [1x3x256x256]
- Number of parameters: 0.818M, 3.377M
- Model size: 3.40MB, 13.4MB
- Output shape: [1x896x12,1x896x1], [1,1x31x4,1x128x128]
Source model repository: MediaPipe-Pose
Performance Reference
Please search model by model name in Model Farm
Inference & Model Conversion
Please search model by model name in Model Farm
License
Source Model: APACHE-2.0
Deployable Model: APLUX-MODEL-FARM-LICENSE