Abstract. We show how to exploit temporal periodicity of moving objects to perform 3D reconstruction. The collection of period-separated frames serve as a surrogate for multiple rigid views of a particular pose of the moving target, thus allowing the use of standard techniques of multiview geometry. We motivate our approach using human motion capture data, for which the true 3D positions of the markers are known. We next apply our approach to image sequences of pedestrians captured with a camcorder. Applications of our proposed approach include 3D motion capture of natural and manmade periodic moving targets from monocular video sequences.
Serge J. Belongie, Josh Wills