DPFM: Deep Partial Functional Maps - Département d'informatique Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

DPFM: Deep Partial Functional Maps

Résumé

We consider the problem of computing dense correspondences between non-rigid shapes with potentially significant partiality. Existing formulations tackle this problem through heavy manifold optimization in the spectral domain, given hand-crafted shape descriptors. In this paper, we propose the first learning method aimed directly at partial non-rigid shape correspondence. Our approach uses the functional map framework, can be trained in a supervised or unsupervised manner, and learns descriptors directly from the data, thus both improving robustness and accuracy in challenging cases. Furthermore, unlike existing techniques, our method is also applicable to partial-to-partial non-rigid matching, in which the common regions on both shapes are unknown a priori. We demonstrate that the resulting method is data-efficient, and achieves state-of-the-art results on several benchmark datasets. Our code and data can be found online
Fichier principal
Vignette du fichier
2110.09994.pdf (24.83 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03938020 , version 1 (14-01-2023)

Identifiants

Citer

Souhaib Attaiki, Gautam Pai, Maks Ovsjanikov. DPFM: Deep Partial Functional Maps. 3DV 2021 - The 9th International Conference on 3D Vision, Dec 2021, Virtual, United Kingdom. pp.175-185, ⟨10.1109/3dv53792.2021.00040⟩. ⟨hal-03938020⟩
28 Consultations
3 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More