Estimating the 3D motion of humans or animals is a fundamental problem in many applications, including realistic character animation for games and movies, or motion analysis for medical diagnostics and sport science. This paper proposes a method for capturing the performance of a human or an animal from a multi-view video sequence. Given an articulated template model and silhouettes from a multi-view image sequence, our approach recovers not only the movement of the skeleton, but also the possibly non-rigid temporal deformation of the 3D surface. While large scale deformations or fast movements are captured by the skeleton pose and approximate surface skinning, true small scale deformations or non-rigid garment motion are captured by fitting the surface to the silhouette. We further propose a novel optimization scheme for skeleton-based pose estimation that exploits the skeleton`s tree structure to split the optimization problem into a local one and a lower dimensional global one. We show on various sequences that our approach can capture the 3D motion of animals and humans accurately even in the case of rapid movements and wide apparel like skirts. http://www.youtube.com/watch?v=qCz68ukbZ7k
© Copyright 2009 IEEE/CVF Conference on Computer Vision and Pattern Recognition. IEEE. All rights reserved.