A Kinematic Chain Space for Monocular Motion Capture
It addresses motion capture for applications like robotics or animation without needing specific camera motion, training data, or constraints, though it appears incremental as it builds on existing kinematic modeling.
The paper tackles monocular motion capture of kinematic chains like human skeletons from uncalibrated camera sequences by projecting observations into a kinematic chain space and optimizing the nuclear norm to enforce structural properties, achieving state-of-the-art results on benchmarks and real-world scenes.
This paper deals with motion capture of kinematic chains (e.g. human skeletons) from monocular image sequences taken by uncalibrated cameras. We present a method based on projecting an observation into a kinematic chain space (KCS). An optimization of the nuclear norm is proposed that implicitly enforces structural properties of the kinematic chain. Unlike other approaches our method does not require specific camera or object motion and is not relying on training data or previously determined constraints such as particular body lengths. The proposed algorithm is able to reconstruct scenes with limited camera motion and previously unseen motions. It is not only applicable to human skeletons but also to other kinematic chains for instance animals or industrial robots. We achieve state-of-the-art results on different benchmark data bases and real world scenes.