Deep Orientation-Aware Functional Maps: Tackling Symmetry Issues in Shape Matching - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Deep Orientation-Aware Functional Maps: Tackling Symmetry Issues in Shape Matching

Résumé

State-of-the-art fully intrinsic networks for non-rigid shape matching often struggle to disambiguate the symmetries of the shapes leading to unstable correspondence predictions. Meanwhile, recent advances in the functional map framework allow to enforce orientation preservation using a functional representation for tangent vector field transfer, through so-called complex functional maps. Using this representation, we propose a new deep learning approach to learn orientation-aware features in a fully unsupervised setting. Our architecture is built on top of DiffusionNet, making it robust to discretization changes. Additionally, we introduce a vector field-based loss, which promotes orientation preservation without using (often unstable) ex- trinsic descriptors.
Fichier principal
Vignette du fichier
Deep_Q_Maps____Hal.pdf (21.79 Mo) Télécharger le fichier
Origine : Accord explicite pour ce dépôt

Dates et versions

hal-03654308 , version 1 (28-04-2022)

Identifiants

Citer

Nicolas Donati, Etienne Corman, Maks Ovsjanikov. Deep Orientation-Aware Functional Maps: Tackling Symmetry Issues in Shape Matching. CVPR 2022 - IEEE/CVF Conference on Computer Vision and Pattern Recognition, Jun 2022, New Orleans, LA, United States. ⟨10.48550/arXiv.2204.13453⟩. ⟨hal-03654308⟩
47 Consultations
7 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More