A fast 3D reconstruction of inextensible surfaces using adaptive weights

Abstract

Recovering the 3D surface of a nonrigid surface from a single viewpoint is known to be both ambiguous and challenging. It has been shown that preventing the surface from either shrinking or stretching is an effective way to resolve the ambiguities inherent to this problem. State-of-the-art solutions to nonrigid 3D shape recovery rely on the fact that distances between adjacent surface points must be preserved. Although the results obtained with such a constrained have small reconstruction error, they are still far away from a real-time reconstruction. The authors therefore exploit a two-level weighting schema in a new approach to inextensible and smooth surface reconstruction. This approach enables a fast and accurate implementation. Furthermore, the tradeoff between the speed and accuracy of reconstruction can be easily controlled with the aid of adaptive weighting of inextensibility constraint in the minimization procedure. Hence, with and appropriate two-level weight coefficient, the new approach provides a satisfactory result, both visually and quantitatively.