Mitsubishi Electric Research Laboratories, Inc.

Mitsubishi Electric Information Technology Center America, Inc (ita)

Michael E Leventon

William T Freeman

Sarah F F Gibson

A method generates a surface model for a three-dimensional object. The object is scanned from a plurality of directions to produce a volume data for each scanning direction. Each volume data is segmented to extract data associated with the object. The volume data are then registered to a common coordinate frame. After registration, a surface net is initialized for each volume data. The multiple surface nets are relaxed and merge according to the common coordinate frame to generate a renderable surface model.

Surface model generation for visualizing three-dimensional objects using multiple elastic surface nets

A system is provided for reconstructing the 3-dimensional motions of a hu figure from a monocularly viewed image sequence in which a statistical approach is used coupled with the use of a set of motion capture examples to build a gaussian probability model for short human motion sequences. In a simplified rendering domain, this yields an optimal 3-d estimate of human motion used to create realistic animations given a 2-d temporal sequence. The subject system is also useful to identify which motion modes are difficult to estimate. In one embodiment, a stick figure is overlaid on the input video image to allow manual correction of incorrectly tracked body parts. The utilization of stick figure correction permits manual correction for a more accurate 3-d reconstruction of the motion depicted in the input video sequence. An interactive tracking system processes real video sequences, and achieves good 3-d reconstructions of the human figure motion.

Growing community of inventors

Cambridge, MA, United States of America

Michael E Leventon