Gframes: Gradient-based local reference frame for 3D shape matching

Simone Melzi, Riccardo Spezialetti, Federico Tombari, Michael M. Bronstein, Luigi DI Stefano, Emanuele Rodola

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

We introduce GFrames, a novel local reference frame (LRF) construction for 3D meshes and point clouds. GFrames are based on the computation of the intrinsic gradient of a scalar field defined on top of the input shape. The resulting tangent vector field defines a repeatable tangent direction of the local frame at each point; importantly, it directly inherits the properties and invariance classes of the underlying scalar function, making it remarkably robust under strong sampling artifacts, vertex noise, as well as non-rigid deformations. Existing local descriptors can directly benefit from our repeatable frames, as we showcase in a selection of 3D vision and shape analysis applications where we demonstrate state-of-the-art performance in a variety of challenging settings.

Original languageEnglish
Title of host publicationProceedings - 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019
PublisherIEEE Computer Society
Pages4624-4633
Number of pages10
ISBN (Electronic)9781728132938
DOIs
StatePublished - Jun 2019
Externally publishedYes
Event32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019 - Long Beach, United States
Duration: 16 Jun 201920 Jun 2019

Publication series

NameProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Volume2019-June
ISSN (Print)1063-6919

Conference

Conference32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019
Country/TerritoryUnited States
CityLong Beach
Period16/06/1920/06/19

Keywords

  • 3D from Multiview and Sensors
  • Categorization
  • Low-level Vision
  • Motion and Tracking
  • Recognition: Detection
  • Retrieval

Fingerprint

Dive into the research topics of 'Gframes: Gradient-based local reference frame for 3D shape matching'. Together they form a unique fingerprint.

Cite this