Publication

Probabilistic simultaneous pose and non-rigid shape recovery

Conference Article

Conference

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

Edition

2011

Pages

1289-1296

Doc link

http://dx.doi.org/10.1109/CVPR.2011.5995532

File

Download the digital copy of the doc pdf document

Abstract

We present an algorithm to simultaneously recover non- rigid shape and camera poses from point correspondences between a reference shape and a sequence of input images. The key novel contribution of our approach is in bringing the tools of the probabilistic SLAM methodology from a rigid to a deformable domain. Under the assumption that the shape may be represented as a weighted sum of deformation modes, we show that the problem of estimating the modal weights along with the camera poses, may be probabilistically formulated as a maximum a posterior estimate and solved using an iterative least squares optimization.

An extensive evaluation on synthetic and real data, shows that our approach has several significant advantages over current approaches, such as performing robustly under large amounts of noise and outliers, and neither requiring to track points over the whole sequence nor initializations close from the ground truth solution.

Categories

computer vision.

Scientific reference

F. Moreno-Noguer and J.M. Porta. Probabilistic simultaneous pose and non-rigid shape recovery, 2011 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2011, Colorado Springs, pp. 1289-1296, IEEE Press.