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.

Gframes: Gradient-based local reference frame for 3D shape matching / S. Melzi; R. Spezialetti; F. Tombari; M. M. Bronstein; L. Di Stefano; E. Rodolà. - ELETTRONICO. - 2019:(2019), pp. 8953995.4624-8953995.4633. (Intervento presentato al convegno 32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019 tenutosi a usa nel 2019) [10.1109/CVPR.2019.00476].

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

R. Spezialetti;L. Di Stefano;
2019

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.
2019
Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
4624
4633
Gframes: Gradient-based local reference frame for 3D shape matching / S. Melzi; R. Spezialetti; F. Tombari; M. M. Bronstein; L. Di Stefano; E. Rodolà. - ELETTRONICO. - 2019:(2019), pp. 8953995.4624-8953995.4633. (Intervento presentato al convegno 32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019 tenutosi a usa nel 2019) [10.1109/CVPR.2019.00476].
S. Melzi; R. Spezialetti; F. Tombari; M. M. Bronstein; L. Di Stefano; E. Rodolà
File in questo prodotto:
Eventuali allegati, non sono esposti

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11585/737542
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 15
  • ???jsp.display-item.citation.isi??? 8
social impact