3D Human Body Morphing Based on Shape Interpolation

With the development of online apparel retailing, the shape of the human body becomes the keystone when evaluating the fit/ease information in the cyberspace. In this paper, we present a method to interpolate the body shape between two arbitrary scanned human bodies. The target shape is first segmented into head, left arm, right arm, left leg, right leg and torso to form a skeleton structure automatically. The pose difference among the scanned human bodies is then adjusted based on the skeleton-driven skin deformation. A slice-by-slice resampling procedure is initiated after the pose synchronization. The resampled points cloud is then employed to reconstruct the new body shape. The final visual effects and the measurements validate that this method is a fast and robust shape interpolation approach, which is very helpful in determining the avatar for the customer in the cyberspace.