Title: Robust Model-Free Tracking of Non-Rigid Shape

(NYU-CS-TR840)

Authors: Lorenzo Torresani, Aaron Hertzmann, and Christoph Bregler

Abstract:
We present a robust algorithm for estimating non-rigid motion in video
sequences. We build on recent methods for tracking video by enforcing
global structure (such as rank constraints) on the tracking. These methods
assume color constancy in the neighborhood of each tracked feature, an
assumption that is violated by occlusions, deformations, lighting changes,
and other effects. Our method identifies outliers while solving for flow.
This allows us to obtain high-quality tracking from difficult sequences,
even when there is no single "reference frame" in which all tracks are
visible.