Pose2met: a unified spatiotemporal framework for 3D human pose estimation and energy expenditure estimation

Key Points

• The research aims to develop a unified framework to accurately estimate 3D human pose and energy expenditure.
• Develop a spatiotemporal framework combining pose estimation and energy expenditure models.
• Utilize high-quality motion representations to enhance accuracy in estimations.
• Apply the framework to various fitness and healthcare scenarios.
• Pose2Met exhibits strong performance in both 3D human pose estimation and energy expenditure estimation.
• The model provides insights into optimizing health and fitness applications through accurate data.