Recovering non-rigid 3D shape from image streams

DMCA

Recovering non-rigid 3D shape from image streams (2000)

Cached

Download Links

Other Repositories/Bibliography

DBLP

by Christoph Bregler , Aaron Hertzmann , Henning Biermann

Venue:	Conf. on Computer Vision and Pattern Recognition
Citations:	270 - 7 self

BibTeX

@INPROCEEDINGS{Bregler00recoveringnon-rigid,
    author = {Christoph Bregler and Aaron Hertzmann and Henning Biermann},
    title = {Recovering non-rigid 3D shape from image streams},
    booktitle = {Conf. on Computer Vision and Pattern Recognition},
    year = {2000}
}

OpenURL

Abstract

This paper addresses the problem of recovering 3D nonrigid shape models from image sequences. For example, given a video recording of a talking person, we would like to estimate a 3D model of the lips and the full face and its internal modes of variation. Many solutions that recover 3D shape from 2D image sequences have been proposed; these so-called structure-from-motion techniques usually assume that the 3D object is rigid. For example Tomasi and Kanade’s factorization technique is based on a rigid shape matrix, which produces a tracking matrix of rank 3 under orthographic projection. We propose a novel technique based on a non-rigid model, where the 3D shape in each frame is a linear combination of a set of basis shapes. Under this model, the tracking matrix is of higher rank, and can be factored in a three step process to yield to pose, configuration and shape. We demonstrate this simple but effective algorithm on video sequences of people and animals. We were able to recover 3D non-rigid facial models with high accuracy. 1

Keyphrases

image stream image sequence orthographic projection rigid shape matrix non-rigid facial model step process high accuracy internal mode novel technique video recording basis shape effective algorithm nonrigid shape model full face example tomasi factorization technique many solution linear combination so-called structure-from-motion technique video sequence non-rigid model

DMCA