Temperature distribution descriptor for robust 3D shape retrieval

Yi Fang, Mengtian Sun, Karthik Ramani

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

Abstract

Recent developments in acquisition techniques are resulting in a very rapid growth of the number of available three dimensional (3D) models across areas as diverse as engineering, medicine and biology. It is therefore of great interest to develop the efficient shape retrieval engines that, given a query object, return similar 3D objects. The performance of a shape retrieval engine is ultimately determined by the quality and characteristics of the shape descriptor used for shape representation. In this paper, we develop a novel shape descriptor, called temperature distribution (TD) descriptor, which is capable of exploring the intrinsic geometric features on the shape. It intuitively interprets the shape in an isometrically-invariant, shape-aware, noise and small topological changes insensitive way. TD descriptor is driven by by heat kernel. The TD descriptor understands the shape by evaluating the surface temperature distribution evolution with time after applying unit heat at each vertex. The TD descriptor is represented in a concise form of a one dimensional (1D) histogram, and captures enough information to robustly handle the shape matching and retrieval process. Experimental results demonstrate the effectiveness of TD descriptor within applications of 3D shape matching and searching for the models at different poses and various noise levels.

Original languageEnglish (US)
Title of host publication2011 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2011
DOIs
StatePublished - Oct 31 2011
Event2011 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2011 - Colorado Springs, CO, United States
Duration: Jun 20 2011Jun 25 2011

Other

Other2011 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2011
CountryUnited States
CityColorado Springs, CO
Period6/20/116/25/11

Fingerprint

Temperature distribution
Engines
Medicine
Hot Temperature

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering

Cite this

Fang, Y., Sun, M., & Ramani, K. (2011). Temperature distribution descriptor for robust 3D shape retrieval. In 2011 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2011 [5981684] https://doi.org/10.1109/CVPRW.2011.5981684

Temperature distribution descriptor for robust 3D shape retrieval. / Fang, Yi; Sun, Mengtian; Ramani, Karthik.

2011 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2011. 2011. 5981684.

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

Fang, Y, Sun, M & Ramani, K 2011, Temperature distribution descriptor for robust 3D shape retrieval. in 2011 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2011., 5981684, 2011 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2011, Colorado Springs, CO, United States, 6/20/11. https://doi.org/10.1109/CVPRW.2011.5981684
Fang Y, Sun M, Ramani K. Temperature distribution descriptor for robust 3D shape retrieval. In 2011 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2011. 2011. 5981684 https://doi.org/10.1109/CVPRW.2011.5981684
Fang, Yi ; Sun, Mengtian ; Ramani, Karthik. / Temperature distribution descriptor for robust 3D shape retrieval. 2011 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2011. 2011.
@inproceedings{5de86940dd604a5fa51f89d86f3a0692,
title = "Temperature distribution descriptor for robust 3D shape retrieval",
abstract = "Recent developments in acquisition techniques are resulting in a very rapid growth of the number of available three dimensional (3D) models across areas as diverse as engineering, medicine and biology. It is therefore of great interest to develop the efficient shape retrieval engines that, given a query object, return similar 3D objects. The performance of a shape retrieval engine is ultimately determined by the quality and characteristics of the shape descriptor used for shape representation. In this paper, we develop a novel shape descriptor, called temperature distribution (TD) descriptor, which is capable of exploring the intrinsic geometric features on the shape. It intuitively interprets the shape in an isometrically-invariant, shape-aware, noise and small topological changes insensitive way. TD descriptor is driven by by heat kernel. The TD descriptor understands the shape by evaluating the surface temperature distribution evolution with time after applying unit heat at each vertex. The TD descriptor is represented in a concise form of a one dimensional (1D) histogram, and captures enough information to robustly handle the shape matching and retrieval process. Experimental results demonstrate the effectiveness of TD descriptor within applications of 3D shape matching and searching for the models at different poses and various noise levels.",
author = "Yi Fang and Mengtian Sun and Karthik Ramani",
year = "2011",
month = "10",
day = "31",
doi = "10.1109/CVPRW.2011.5981684",
language = "English (US)",
isbn = "9781457705298",
booktitle = "2011 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2011",

}

TY - GEN

T1 - Temperature distribution descriptor for robust 3D shape retrieval

AU - Fang, Yi

AU - Sun, Mengtian

AU - Ramani, Karthik

PY - 2011/10/31

Y1 - 2011/10/31

N2 - Recent developments in acquisition techniques are resulting in a very rapid growth of the number of available three dimensional (3D) models across areas as diverse as engineering, medicine and biology. It is therefore of great interest to develop the efficient shape retrieval engines that, given a query object, return similar 3D objects. The performance of a shape retrieval engine is ultimately determined by the quality and characteristics of the shape descriptor used for shape representation. In this paper, we develop a novel shape descriptor, called temperature distribution (TD) descriptor, which is capable of exploring the intrinsic geometric features on the shape. It intuitively interprets the shape in an isometrically-invariant, shape-aware, noise and small topological changes insensitive way. TD descriptor is driven by by heat kernel. The TD descriptor understands the shape by evaluating the surface temperature distribution evolution with time after applying unit heat at each vertex. The TD descriptor is represented in a concise form of a one dimensional (1D) histogram, and captures enough information to robustly handle the shape matching and retrieval process. Experimental results demonstrate the effectiveness of TD descriptor within applications of 3D shape matching and searching for the models at different poses and various noise levels.

AB - Recent developments in acquisition techniques are resulting in a very rapid growth of the number of available three dimensional (3D) models across areas as diverse as engineering, medicine and biology. It is therefore of great interest to develop the efficient shape retrieval engines that, given a query object, return similar 3D objects. The performance of a shape retrieval engine is ultimately determined by the quality and characteristics of the shape descriptor used for shape representation. In this paper, we develop a novel shape descriptor, called temperature distribution (TD) descriptor, which is capable of exploring the intrinsic geometric features on the shape. It intuitively interprets the shape in an isometrically-invariant, shape-aware, noise and small topological changes insensitive way. TD descriptor is driven by by heat kernel. The TD descriptor understands the shape by evaluating the surface temperature distribution evolution with time after applying unit heat at each vertex. The TD descriptor is represented in a concise form of a one dimensional (1D) histogram, and captures enough information to robustly handle the shape matching and retrieval process. Experimental results demonstrate the effectiveness of TD descriptor within applications of 3D shape matching and searching for the models at different poses and various noise levels.

UR - http://www.scopus.com/inward/record.url?scp=80054920864&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80054920864&partnerID=8YFLogxK

U2 - 10.1109/CVPRW.2011.5981684

DO - 10.1109/CVPRW.2011.5981684

M3 - Conference contribution

SN - 9781457705298

BT - 2011 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2011

ER -