SRFeat: Learning Locally Accurate and Globally Consistent Non-Rigid Shape Correspondence - Archive ouverte HAL
Communication Dans Un Congrès Année : 2022

SRFeat: Learning Locally Accurate and Globally Consistent Non-Rigid Shape Correspondence

Résumé

In this work, we present a novel learning-based framework that combines the local accuracy of contrastive learning with the global consistency of geometric approaches, for robust non-rigid matching. We first observe that while contrastive learning can lead to powerful point-wise features, the learned correspondences commonly lack smoothness and consistency, owing to the purely combinatorial nature of the standard contrastive losses. To overcome this limitation we propose to boost contrastive feature learning with two types of smoothness regularization that inject geometric information into correspondence learning. With this novel combination in hand, the resulting features are both highly discriminative across individual points, and, at the same time, lead to robust and consistent correspondences, through simple proximity queries. Our framework is general and is applicable to local feature learning in both the 3D and 2D domains. We demonstrate the superiority of our approach through extensive experiments on a wide range of challenging matching benchmarks, including 3D non-rigid shape correspondence and 2D image keypoint matching.

Domaines

Informatique
Fichier principal
Vignette du fichier
SRFeat_3DV22.pdf (18.84 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04352313 , version 1 (19-12-2023)

Identifiants

Citer

Lei Li, Souhaib Attaiki, Maks Ovsjanikov. SRFeat: Learning Locally Accurate and Globally Consistent Non-Rigid Shape Correspondence. 2022 International Conference on 3D Vision (3DV), Sep 2022, Prague, Czech Republic. ⟨10.1109/3DV57658.2022.00027⟩. ⟨hal-04352313⟩
26 Consultations
16 Téléchargements

Altmetric

Partager

More