Recovering 3D models from silhouette sequences and detecting unexposed regions

This paper recovers 3D shapes from contours for graphics display in a 3D virtual environment. In this method, a continuous sequence of images is taken as an object rotates, and smooth convex shape is estimated instantaneously from its contour and contour movement. Shapes also are analyzed that do not satisfy the conditions of smoothness and visibility, which are indispensable for modeling an object. A region that is not exposed as contour yields a non-smoothness in the tracked contour movement. An unknown region is obtained for further investigation using other visual cues. The entire process from silhouettes to a 3D model is based on local computation; which is promising for producing shapes in real time. The direct goal is to establish 3D graphics models of human faces for the growing needs of visual communications. Some good results have been obtained.