Center-shift: An approach towards automatic robust mesh segmentation (ARMS)

Mengtian Sun, Yi Fang, Karthik Ramani

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In the area of 3D shape analysis, research in mesh segmentation has always been an important topic, as it is a fundamental low-level task which can be utilized in many applications including computer-aided design, computer animation, biomedical applications and many other fields. We define the automatic robust mesh segmentation (ARMS) method in this paper, which 1) is invariant to isometric transformation, 2) is insensitive to noise and deformation, 3) performs closely to human perception, 4) is efficient in computation, and 5) is minimally dependent on prior knowledge. In this work, we develop a new framework, namely the Center-Shift, which discovers meaningful segments of a 3D object by exploring the intrinsic geometric structure encoded in the biharmonic kernel. Our Center-Shift framework has three main steps: First, we construct a feature space where every vertex on the mesh surface is associated with the corresponding biharmonic kernel density function value. Second, we apply the Center-Shift algorithm for initial segmentation. Third, the initial segmentation result is refined through an efficient iterative process which leads to visually salient segmentation of the shape. The performance of this segmentation method is demonstrated through extensive experiments on various sets of 3D shapes and different types of noise and deformation. The experimental results of 3D shape segmentation have shown better performance of Center-Shift, compared to state-of-the-art segmentation methods.

Original languageEnglish (US)
Title of host publication2012 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2012
Pages630-637
Number of pages8
DOIs
StatePublished - Oct 1 2012
Event2012 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2012 - Providence, RI, United States
Duration: Jun 16 2012Jun 21 2012

Other

Other2012 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2012
CountryUnited States
CityProvidence, RI
Period6/16/126/21/12

Fingerprint

Animation
Probability density function
Computer aided design
Experiments

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition

Cite this

Sun, M., Fang, Y., & Ramani, K. (2012). Center-shift: An approach towards automatic robust mesh segmentation (ARMS). In 2012 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2012 (pp. 630-637). [6247730] https://doi.org/10.1109/CVPR.2012.6247730

Center-shift : An approach towards automatic robust mesh segmentation (ARMS). / Sun, Mengtian; Fang, Yi; Ramani, Karthik.

2012 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2012. 2012. p. 630-637 6247730.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Sun, M, Fang, Y & Ramani, K 2012, Center-shift: An approach towards automatic robust mesh segmentation (ARMS). in 2012 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2012., 6247730, pp. 630-637, 2012 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2012, Providence, RI, United States, 6/16/12. https://doi.org/10.1109/CVPR.2012.6247730
Sun M, Fang Y, Ramani K. Center-shift: An approach towards automatic robust mesh segmentation (ARMS). In 2012 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2012. 2012. p. 630-637. 6247730 https://doi.org/10.1109/CVPR.2012.6247730
Sun, Mengtian ; Fang, Yi ; Ramani, Karthik. / Center-shift : An approach towards automatic robust mesh segmentation (ARMS). 2012 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2012. 2012. pp. 630-637
@inproceedings{60355f4c876546d4ba6ab5662d2a447d,
title = "Center-shift: An approach towards automatic robust mesh segmentation (ARMS)",
abstract = "In the area of 3D shape analysis, research in mesh segmentation has always been an important topic, as it is a fundamental low-level task which can be utilized in many applications including computer-aided design, computer animation, biomedical applications and many other fields. We define the automatic robust mesh segmentation (ARMS) method in this paper, which 1) is invariant to isometric transformation, 2) is insensitive to noise and deformation, 3) performs closely to human perception, 4) is efficient in computation, and 5) is minimally dependent on prior knowledge. In this work, we develop a new framework, namely the Center-Shift, which discovers meaningful segments of a 3D object by exploring the intrinsic geometric structure encoded in the biharmonic kernel. Our Center-Shift framework has three main steps: First, we construct a feature space where every vertex on the mesh surface is associated with the corresponding biharmonic kernel density function value. Second, we apply the Center-Shift algorithm for initial segmentation. Third, the initial segmentation result is refined through an efficient iterative process which leads to visually salient segmentation of the shape. The performance of this segmentation method is demonstrated through extensive experiments on various sets of 3D shapes and different types of noise and deformation. The experimental results of 3D shape segmentation have shown better performance of Center-Shift, compared to state-of-the-art segmentation methods.",
author = "Mengtian Sun and Yi Fang and Karthik Ramani",
year = "2012",
month = "10",
day = "1",
doi = "10.1109/CVPR.2012.6247730",
language = "English (US)",
isbn = "9781467312264",
pages = "630--637",
booktitle = "2012 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2012",

}

TY - GEN

T1 - Center-shift

T2 - An approach towards automatic robust mesh segmentation (ARMS)

AU - Sun, Mengtian

AU - Fang, Yi

AU - Ramani, Karthik

PY - 2012/10/1

Y1 - 2012/10/1

N2 - In the area of 3D shape analysis, research in mesh segmentation has always been an important topic, as it is a fundamental low-level task which can be utilized in many applications including computer-aided design, computer animation, biomedical applications and many other fields. We define the automatic robust mesh segmentation (ARMS) method in this paper, which 1) is invariant to isometric transformation, 2) is insensitive to noise and deformation, 3) performs closely to human perception, 4) is efficient in computation, and 5) is minimally dependent on prior knowledge. In this work, we develop a new framework, namely the Center-Shift, which discovers meaningful segments of a 3D object by exploring the intrinsic geometric structure encoded in the biharmonic kernel. Our Center-Shift framework has three main steps: First, we construct a feature space where every vertex on the mesh surface is associated with the corresponding biharmonic kernel density function value. Second, we apply the Center-Shift algorithm for initial segmentation. Third, the initial segmentation result is refined through an efficient iterative process which leads to visually salient segmentation of the shape. The performance of this segmentation method is demonstrated through extensive experiments on various sets of 3D shapes and different types of noise and deformation. The experimental results of 3D shape segmentation have shown better performance of Center-Shift, compared to state-of-the-art segmentation methods.

AB - In the area of 3D shape analysis, research in mesh segmentation has always been an important topic, as it is a fundamental low-level task which can be utilized in many applications including computer-aided design, computer animation, biomedical applications and many other fields. We define the automatic robust mesh segmentation (ARMS) method in this paper, which 1) is invariant to isometric transformation, 2) is insensitive to noise and deformation, 3) performs closely to human perception, 4) is efficient in computation, and 5) is minimally dependent on prior knowledge. In this work, we develop a new framework, namely the Center-Shift, which discovers meaningful segments of a 3D object by exploring the intrinsic geometric structure encoded in the biharmonic kernel. Our Center-Shift framework has three main steps: First, we construct a feature space where every vertex on the mesh surface is associated with the corresponding biharmonic kernel density function value. Second, we apply the Center-Shift algorithm for initial segmentation. Third, the initial segmentation result is refined through an efficient iterative process which leads to visually salient segmentation of the shape. The performance of this segmentation method is demonstrated through extensive experiments on various sets of 3D shapes and different types of noise and deformation. The experimental results of 3D shape segmentation have shown better performance of Center-Shift, compared to state-of-the-art segmentation methods.

UR - http://www.scopus.com/inward/record.url?scp=84866684723&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84866684723&partnerID=8YFLogxK

U2 - 10.1109/CVPR.2012.6247730

DO - 10.1109/CVPR.2012.6247730

M3 - Conference contribution

AN - SCOPUS:84866684723

SN - 9781467312264

SP - 630

EP - 637

BT - 2012 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2012

ER -