Publication
Capturing 3D stretchable surfaces from single images in closed form
Conference Article
Conference
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Edition
2009
Pages
1842-1849
Doc link
http://dx.doi.org/10.1109/CVPRW.2009.5206758
File
Authors
-
Moreno Noguer, Francesc
-
Salzmann, Mathieu
-
Lepetit, Vincent
-
Fua, Pascal
Projects associated
PACOPLUS: Perception, action & cognition through learning of object-action complexes.
MIPRCV: CONSOLIDER-INGENIO 2010 Multimodal interaction in pattern recognition and computer vision
PAU: Percepción y acción ante incertidumbre
BPnP: Priors para la detección 3D en tiempo real de objetos rígidos y deformables
Abstract
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.
Categories
computer vision, object detection, pose estimation.
Author keywords
deformable surfaces, 3D reconstruction
Scientific reference
F. Moreno-Noguer, M. Salzmann, V. Lepetit and P. Fua. Capturing 3D stretchable surfaces from single images in closed form, 2009 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2009, Miami, FL, USA, pp. 1842-1849, IEEE.
Follow us!