Functional Faces:: Groupwise Dense Correspondence using Functional Maps

Chao Zhang; William Alfred Peter Smith; Arnaud Fabien Dessein; Nicholas Edwin Pears; Hang Dai

Functional Faces: Groupwise Dense Correspondence using Functional Maps

Chao Zhang, William Alfred Peter Smith, Arnaud Fabien Dessein, Nicholas Edwin Pears, Hang Dai

Computer Science

Research output: Contribution to conference › Paper › peer-review

Abstract

In this paper we present a method for computing dense correspondence between a set of 3D face meshes using functional maps. The functional maps paradigm brings with it a number of advantages for face correspondence. First, it allows us to combine various notions of correspondence. We do so by proposing a number of face-specific functions, suited to either within- or between-subject correspondence. Second, we propose a groupwise variant of the method allowing us to compute cycle-consistent functional maps between all faces in a training set. Since functional maps are of much lower dimension than point-to-point correspondences, this is feasible even when the input meshes are very high resolution. Finally, we show how a functional map provides a geometric constraint that can be used to filter feature matches between non-rigidly deforming surfaces.

Original language	English
Pages	5033-5041
Number of pages	9
Publication status	Published - 26 Jun 2016

Access to Document

http://www.cv-foundation.org/openaccess/content_cvpr_2016/html/Zhang_Functional_Faces_Groupwise_CVPR_2016_paper.html

Cite this

@conference{0bec9e26f5ac4593a324e9b6b8c23cf6,

title = "Functional Faces:: Groupwise Dense Correspondence using Functional Maps",

abstract = "In this paper we present a method for computing dense correspondence between a set of 3D face meshes using functional maps. The functional maps paradigm brings with it a number of advantages for face correspondence. First, it allows us to combine various notions of correspondence. We do so by proposing a number of face-specific functions, suited to either within- or between-subject correspondence. Second, we propose a groupwise variant of the method allowing us to compute cycle-consistent functional maps between all faces in a training set. Since functional maps are of much lower dimension than point-to-point correspondences, this is feasible even when the input meshes are very high resolution. Finally, we show how a functional map provides a geometric constraint that can be used to filter feature matches between non-rigidly deforming surfaces.",

author = "Chao Zhang and Smith, {William Alfred Peter} and Dessein, {Arnaud Fabien} and Pears, {Nicholas Edwin} and Hang Dai",

year = "2016",

month = jun,

day = "26",

language = "English",

pages = "5033--5041",

}

TY - CONF

T1 - Functional Faces:

T2 - Groupwise Dense Correspondence using Functional Maps

AU - Zhang, Chao

AU - Smith, William Alfred Peter

AU - Dessein, Arnaud Fabien

AU - Pears, Nicholas Edwin

AU - Dai, Hang

PY - 2016/6/26

Y1 - 2016/6/26

N2 - In this paper we present a method for computing dense correspondence between a set of 3D face meshes using functional maps. The functional maps paradigm brings with it a number of advantages for face correspondence. First, it allows us to combine various notions of correspondence. We do so by proposing a number of face-specific functions, suited to either within- or between-subject correspondence. Second, we propose a groupwise variant of the method allowing us to compute cycle-consistent functional maps between all faces in a training set. Since functional maps are of much lower dimension than point-to-point correspondences, this is feasible even when the input meshes are very high resolution. Finally, we show how a functional map provides a geometric constraint that can be used to filter feature matches between non-rigidly deforming surfaces.

AB - In this paper we present a method for computing dense correspondence between a set of 3D face meshes using functional maps. The functional maps paradigm brings with it a number of advantages for face correspondence. First, it allows us to combine various notions of correspondence. We do so by proposing a number of face-specific functions, suited to either within- or between-subject correspondence. Second, we propose a groupwise variant of the method allowing us to compute cycle-consistent functional maps between all faces in a training set. Since functional maps are of much lower dimension than point-to-point correspondences, this is feasible even when the input meshes are very high resolution. Finally, we show how a functional map provides a geometric constraint that can be used to filter feature matches between non-rigidly deforming surfaces.

M3 - Paper

SP - 5033

EP - 5041

ER -