To handle the nonrigid background like a sea, we also propose a robust fusion mechanism between motion and appearance-based features.
Existing marker-less motion capture methods often assume known backgrounds, static cameras, and sequence specific motion priors, which narrows its application scenarios.
Second, we define a general parametrization of body pose and a new, multi-stage, method to estimate 3D pose from 2D joint locations using an over-complete dictionary of poses.
Ranked #28 on 3D Human Pose Estimation on HumanEva-I
Existing approaches to nonrigid structure from motion assume that the instantaneous 3D shape of a deforming object is a linear combination of basis shapes, which have to be estimated anew for each video sequence.