By the same authors

From the same journal

From the same journal

Curvature-based spectral signatures for non-rigid shape retrieval

Research output: Contribution to journalArticle

Author(s)

Department/unit(s)

Publication details

JournalComputer Vision and Image Understanding
DateAccepted/In press - 1 Apr 2018
DateE-pub ahead of print (current) - 17 Apr 2018
Number of pages13
Early online date17/04/18
Original languageEnglish

Abstract

The geometric properties of descriptors derived from the diusion geometry family have many valuable
properties for shape analysis. These descriptors, also known as diusion distances, use the eigenvalues
and eigenfunctions of the Laplace-Beltrami operator to construct invariant metrics about the
shape. Although they are invariant to many transformations, non-rigid deformations still modify the
shape spectrum. In this paper, we propose a shape descriptor framework based on a Lagrangian formulation
of dynamics on the surface of the object. We show how our framework can be applied to
non-rigid shape retrieval, once it benefits from the analysis and the automatic identification of shape
joints, using a curvature-based scheme to identify these regions. We also propose modifications to
the Improved Wave Kernel Signature in order to keep descriptors more stable against non-rigid deformations.
We compare our spectral components with the classic ones and our spectral framework with
state-of-the-art non-rigid signatures on traditional benchmarks, showing that our shape spectra is more
stable and discriminative and clearly outperforms other descriptors in the SHREC’10, SHREC’11 and
SHREC’17 benchmarks.

Bibliographical note

© 2018 Elsevier Inc. This is an author-produced version of the published paper. Uploaded in accordance with the publisher’s self-archiving policy.

Discover related content

Find related publications, people, projects, datasets and more using interactive charts.

View graph of relations