View in EDS HTML Full Text PDF Full Text

Anisotropic Diffusion Descriptors.

Saved in:
Bibliographic Details
Title: Anisotropic Diffusion Descriptors.
Authors: Boscaini, D.1, Masci, J.1, Rodolà, E.2, Bronstein, M. M.1, Cremers, D.2
Source: Computer Graphics Forum. May2016, Vol. 35 Issue 2, p431-441. 11p. 8 Color Photographs, 2 Graphs.
Subjects: Computer graphics research, Computer art, Digital image processing, Shape analysis (Computational geometry), Computational geometry
Abstract: Spectral methods have recently gained popularity in many domains of computer graphics and geometry processing, especially shape processing, computation of shape descriptors, distances, and correspondence. Spectral geometric structures are intrinsic and thus invariant to isometric deformations, are efficiently computed, and can be constructed on shapes in different representations. A notable drawback of these constructions, however, is that they are isotropic, i.e., insensitive to direction. In this paper, we show how to construct direction-sensitive spectral feature descriptors using anisotropic diffusion on meshes and point clouds. The core of our construction are directed local kernels acting similarly to steerable filters, which are learned in a task-specific manner. Remarkably, while being intrinsic, our descriptors allow to disambiguate reflection symmetries. We show the application of anisotropic descriptors for problems of shape correspondence on meshes and point clouds, achieving results significantly better than state-of-the-art methods. [ABSTRACT FROM AUTHOR]
Copyright of Computer Graphics Forum is the property of Wiley-Blackwell and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
Full text is not displayed to guests.
FullText Links:
  – Type: pdflink
Text:
  Availability: 1
Header DbId: egs
DbLabel: Engineering Source
An: 115774595
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Anisotropic Diffusion Descriptors.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Boscaini%2C+D%2E%22">Boscaini, D.</searchLink><relatesTo>1</relatesTo><br /><searchLink fieldCode="AR" term="%22Masci%2C+J%2E%22">Masci, J.</searchLink><relatesTo>1</relatesTo><br /><searchLink fieldCode="AR" term="%22Rodolà%2C+E%2E%22">Rodolà, E.</searchLink><relatesTo>2</relatesTo><br /><searchLink fieldCode="AR" term="%22Bronstein%2C+M%2E+M%2E%22">Bronstein, M. M.</searchLink><relatesTo>1</relatesTo><br /><searchLink fieldCode="AR" term="%22Cremers%2C+D%2E%22">Cremers, D.</searchLink><relatesTo>2</relatesTo>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Computer+Graphics+Forum%22">Computer Graphics Forum</searchLink>. May2016, Vol. 35 Issue 2, p431-441. 11p. 8 Color Photographs, 2 Graphs.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Computer+graphics+research%22">Computer graphics research</searchLink><br /><searchLink fieldCode="DE" term="%22Computer+art%22">Computer art</searchLink><br /><searchLink fieldCode="DE" term="%22Digital+image+processing%22">Digital image processing</searchLink><br /><searchLink fieldCode="DE" term="%22Shape+analysis+%28Computational+geometry%29%22">Shape analysis (Computational geometry)</searchLink><br /><searchLink fieldCode="DE" term="%22Computational+geometry%22">Computational geometry</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Spectral methods have recently gained popularity in many domains of computer graphics and geometry processing, especially shape processing, computation of shape descriptors, distances, and correspondence. Spectral geometric structures are intrinsic and thus invariant to isometric deformations, are efficiently computed, and can be constructed on shapes in different representations. A notable drawback of these constructions, however, is that they are isotropic, i.e., insensitive to direction. In this paper, we show how to construct direction-sensitive spectral feature descriptors using anisotropic diffusion on meshes and point clouds. The core of our construction are directed local kernels acting similarly to steerable filters, which are learned in a task-specific manner. Remarkably, while being intrinsic, our descriptors allow to disambiguate reflection symmetries. We show the application of anisotropic descriptors for problems of shape correspondence on meshes and point clouds, achieving results significantly better than state-of-the-art methods. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of Computer Graphics Forum is the property of Wiley-Blackwell and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=115774595
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1111/cgf.12844
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 11
        StartPage: 431
    Subjects:
      – SubjectFull: Computer graphics research
        Type: general
      – SubjectFull: Computer art
        Type: general
      – SubjectFull: Digital image processing
        Type: general
      – SubjectFull: Shape analysis (Computational geometry)
        Type: general
      – SubjectFull: Computational geometry
        Type: general
    Titles:
      – TitleFull: Anisotropic Diffusion Descriptors.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Boscaini, D.
      – PersonEntity:
          Name:
            NameFull: Masci, J.
      – PersonEntity:
          Name:
            NameFull: Rodolà, E.
      – PersonEntity:
          Name:
            NameFull: Bronstein, M. M.
      – PersonEntity:
          Name:
            NameFull: Cremers, D.
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 05
              Text: May2016
              Type: published
              Y: 2016
          Identifiers:
            – Type: issn-print
              Value: 01677055
          Numbering:
            – Type: volume
              Value: 35
            – Type: issue
              Value: 2
          Titles:
            – TitleFull: Computer Graphics Forum
              Type: main
ResultId 1