Publication

Mode-shape interpretation: Re-thinking modal space for recovering deformable shapes

Conference Article

Conference

IEEE Winter Conference on Applications of Computer Vision (WACV)

Edition

2016

Pages

1-8

Doc link

http://dx.doi.org/10.1109/WACV.2016.7477725

File

Download the digital copy of the doc pdf document

Abstract

This paper describes an on-line approach for estimating non-rigid shape and camera pose from monocular video sequences. We assume an initial estimate of the shape at rest to be given and represented by a triangulated mesh, which is encoded by a matrix of the distances between every pair of vertexes. By applying spectral analysis on this matrix, we are then able to compute a low-dimensional shape basis, that in contrast to standard approaches, has a very direct physical interpretation and requires a much smaller number of modes to span a large variety of deformations, either for inextensible or extensible configurations. Based on this low-rank model, we then sequentially retrieve both camera motion and non-rigid shape in each image, optimizing the model parameters with bundle adjustment over a sliding window of image frames. Since the number of these parameters is small, specially when considering physical priors, our approach may potentially achieve real-time performance. Experimental results on real videos for different scenarios demonstrate remarkable robustness to artifacts such as missing and noisy observations.

Categories

computer vision, optimisation.

Scientific reference

A. Agudo, J.M. Martínez, B. Calvo and F. Moreno-Noguer. Mode-shape interpretation: Re-thinking modal space for recovering deformable shapes, 2016 IEEE Winter Conference on Applications of Computer Vision, 2016, Lake Placid, USA, pp. 1-8, IEEE.