Elastic Morphing of 2D and 3D Objects on a Shape Manifold

Authors:
C. Samir;P. Dooren;D. Laurent;K. A. Gallivan;P. -A. Absil
Affiliations:
Dept of Mathematical Engineering, Université catholique de Louvain, Belgium;Dept of Mathematical Engineering, Université catholique de Louvain, Belgium;Dept of Mathematical Engineering, Université catholique de Louvain, Belgium;Dept of Mathematics, Florida State University, Tallahassee, USA 32306;Dept of Mathematical Engineering, Université catholique de Louvain, Belgium
Venue:
ICIAR '09 Proceedings of the 6th International Conference on Image Analysis and Recognition
Year:
2009

Citing 9
Cited 0

Scheduled Fourier volume morphing

SIGGRAPH '92 Proceedings of the 19th annual conference on Computer graphics and interactive techniques
The De Casteljau Algorithm on Lie Groups and Spheres

Journal of Dynamical and Control Systems
Analysis of Planar Shapes Using Geodesic Paths on Shape Spaces

IEEE Transactions on Pattern Analysis and Machine Intelligence
A two-step algorithm of smooth spline generation on Riemannian manifolds

Journal of Computational and Applied Mathematics
Bézier curves and C2 interpolation in Riemannian manifolds

Journal of Approximation Theory
Large Deformation Diffeomorphic Metric Curve Mapping

International Journal of Computer Vision
An Intrinsic Framework for Analysis of Facial Surfaces

International Journal of Computer Vision
Shape matching by variational computation of geodesics on a manifold

DAGM'06 Proceedings of the 28th conference on Pattern Recognition
Geodesics between 3d closed curves using path-straightening

ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part I

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present a new method for morphing 2D and 3D objects. In particular we focus on the problem of smooth interpolation on a shape manifold. The proposed method takes advantage of two recent works on 2D and 3D shape analysis to compute elastic geodesics between any two arbitrary shapes and interpolations on a Riemannian manifold. Given a finite set of frames of the same (2D or 3D) object from a video sequence, or different expressions of a 3D face, our goal is to interpolate between the given data in a manner that is smooth. Experimental results are presented to demonstrate the effectiveness of our method.