Mesh Saliency via Spectral Processing

Ran Song, Yonghuai Liu, Martin Ralph, Paul Rosin

Research output: Contribution to journalArticle

66 Citations (Scopus)
23 Downloads (Pure)

Abstract

We propose a novel method for detecting mesh saliency, a perceptuallybased measure of the importance of a local region on a 3D surface mesh. Our method incorporates global considerations by making use of spectral attributes of the mesh, unlike most existing methods which are typically based on local geometric cues. We first consider the properties of the log- Laplacian spectrum of the mesh. Those frequencies which show differences from expected behaviour capture saliency in the frequency domain. Information about these frequencies is considered in the spatial domain at multiple spatial scales to localise the salient features and give the final salient areas. The effectiveness and robustness of our approach are demonstrated by comparisons to previous approaches on a range of test models. The benefits of the proposed method are further evaluated in applications such as mesh simplification, mesh segmentation and scan integration, where we show how incorporating mesh saliency can provide improved results.
Original languageEnglish
JournalACM Transactions on Graphics
Volume33
Issue number1
Early online date31 Jan 2014
DOIs
Publication statusPublished - Jan 2014

Fingerprint

Processing

Keywords

  • Applications
  • Mesh saliency
  • Mesh segmentation
  • Mesh simplification
  • Spectral mesh processing
  • Algorithms
  • mesh segmentation
  • mesh simplification
  • mesh saliency
  • spectral mesh processing

Cite this

Song, Ran ; Liu, Yonghuai ; Ralph, Martin ; Rosin, Paul. / Mesh Saliency via Spectral Processing. In: ACM Transactions on Graphics. 2014 ; Vol. 33, No. 1.
@article{61556073751a45ed8516b43e1cbb54a5,
title = "Mesh Saliency via Spectral Processing",
abstract = "We propose a novel method for detecting mesh saliency, a perceptuallybased measure of the importance of a local region on a 3D surface mesh. Our method incorporates global considerations by making use of spectral attributes of the mesh, unlike most existing methods which are typically based on local geometric cues. We first consider the properties of the log- Laplacian spectrum of the mesh. Those frequencies which show differences from expected behaviour capture saliency in the frequency domain. Information about these frequencies is considered in the spatial domain at multiple spatial scales to localise the salient features and give the final salient areas. The effectiveness and robustness of our approach are demonstrated by comparisons to previous approaches on a range of test models. The benefits of the proposed method are further evaluated in applications such as mesh simplification, mesh segmentation and scan integration, where we show how incorporating mesh saliency can provide improved results.",
keywords = "Applications, Mesh saliency, Mesh segmentation, Mesh simplification, Spectral mesh processing, Algorithms, mesh segmentation, mesh simplification, mesh saliency, spectral mesh processing",
author = "Ran Song and Yonghuai Liu and Martin Ralph and Paul Rosin",
year = "2014",
month = "1",
doi = "10.1145/2530691",
language = "English",
volume = "33",
journal = "ACM Transactions on Graphics",
number = "1",

}

Mesh Saliency via Spectral Processing. / Song, Ran; Liu, Yonghuai; Ralph, Martin; Rosin, Paul.

In: ACM Transactions on Graphics, Vol. 33, No. 1, 01.2014.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Mesh Saliency via Spectral Processing

AU - Song, Ran

AU - Liu, Yonghuai

AU - Ralph, Martin

AU - Rosin, Paul

PY - 2014/1

Y1 - 2014/1

N2 - We propose a novel method for detecting mesh saliency, a perceptuallybased measure of the importance of a local region on a 3D surface mesh. Our method incorporates global considerations by making use of spectral attributes of the mesh, unlike most existing methods which are typically based on local geometric cues. We first consider the properties of the log- Laplacian spectrum of the mesh. Those frequencies which show differences from expected behaviour capture saliency in the frequency domain. Information about these frequencies is considered in the spatial domain at multiple spatial scales to localise the salient features and give the final salient areas. The effectiveness and robustness of our approach are demonstrated by comparisons to previous approaches on a range of test models. The benefits of the proposed method are further evaluated in applications such as mesh simplification, mesh segmentation and scan integration, where we show how incorporating mesh saliency can provide improved results.

AB - We propose a novel method for detecting mesh saliency, a perceptuallybased measure of the importance of a local region on a 3D surface mesh. Our method incorporates global considerations by making use of spectral attributes of the mesh, unlike most existing methods which are typically based on local geometric cues. We first consider the properties of the log- Laplacian spectrum of the mesh. Those frequencies which show differences from expected behaviour capture saliency in the frequency domain. Information about these frequencies is considered in the spatial domain at multiple spatial scales to localise the salient features and give the final salient areas. The effectiveness and robustness of our approach are demonstrated by comparisons to previous approaches on a range of test models. The benefits of the proposed method are further evaluated in applications such as mesh simplification, mesh segmentation and scan integration, where we show how incorporating mesh saliency can provide improved results.

KW - Applications

KW - Mesh saliency

KW - Mesh segmentation

KW - Mesh simplification

KW - Spectral mesh processing

KW - Algorithms

KW - mesh segmentation

KW - mesh simplification

KW - mesh saliency

KW - spectral mesh processing

UR - http://www.mendeley.com/research/mesh-saliency-via-spectral-processing

U2 - 10.1145/2530691

DO - 10.1145/2530691

M3 - Article

VL - 33

JO - ACM Transactions on Graphics

JF - ACM Transactions on Graphics

IS - 1

ER -