Capturing 3D Stretchable Surfaces from Single Images in Closed Form

We present a closed-form solution to the problem of recovering the 3D shape of a non-rigid potentially stretchable surface from 3D-to-2D correspondences. In other words, we can reconstruct a surface from a single image without a priori knowledge of its deformations in that image. State-of-the-art solutions to non-rigid 3D shape recovery rely on the fact that distances between neighboring surface points must be preserved and are therefore limited to inelastic surfaces. Here, we show that replacing the inextensibility constraints by shading ones removes this limitation while still allowing 3D reconstruction in closed-form. We demonstrate our method and compare it to an earlier one using both synthetic and real data.

• Type: Conference
• Year: 2009
• Where: CVPR
• Authors: Francesc Moreno-Noguer (Institut de Robotica i Informatica industrial (CSIC-UPC), Mathieu Salzmann (University of California, Berkeley), Vincent Lepetit (EPFL), Pascal Fua (EPFL)
• Keywords: Capturing 3D Stretchable Surfaces, Computer Vision, CVPR 2009