Exploring Pose Priors for Human Pose Estimation with Joint Angle Representations
This tackles the issue of pose validity for applications in computer vision and robotics, but appears incremental as it focuses on known constraints like joint angle limits.
The paper addresses the problem of preventing physically impossible poses in human pose estimation by exploring pose priors, but does not report specific results or numbers.
Pose Priors are critical in human pose estimation, since they are able to enforce constraints that prevent estimated poses from tending to physically impossible positions. Human pose generally consists of up to 22 Joint Angles of various segments, and their respective bone lengths, but the way these various segments interact can affect the validity of a pose. Looking at the Knee-Ankle segment alone, we can observe that clearly, the Knee cannot bend forward beyond it's roughly 90 degree point, amongst various other impossible poses below.