Weakly Supervised Deep Functional Map for Shape Matching - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2020

Weakly Supervised Deep Functional Map for Shape Matching

Abstract

A variety of deep functional maps have been proposed recently, from fully supervised to totally unsupervised, with a range of loss functions as well as different regularization terms. However, it is still not clear what are minimum ingredients of a deep functional map pipeline and whether such ingredients unify or generalize all recent work on deep functional maps. We show empirically minimum components for obtaining state of the art results with different loss functions, supervised as well as unsupervised. Furthermore, we propose a novel framework designed for both full-to-full as well as partial to full shape matching that achieves state of the art results on all benchmark datasets outperforming even the fully supervised methods by a significant margin.
Fichier principal
Vignette du fichier
view.pdf (188.49 Ko) Télécharger le fichier
Origin Files produced by the author(s)
Loading...

Dates and versions

hal-02872053 , version 1 (18-06-2020)
hal-02872053 , version 2 (28-09-2020)

Identifiers

  • HAL Id : hal-02872053 , version 2

Cite

Abhishek Sharma, Maks Ovsjanikov. Weakly Supervised Deep Functional Map for Shape Matching. Neurips 2020, Dec 2020, Vancouver (Virtual Conference), Canada. ⟨hal-02872053v2⟩
536 View
485 Download

Share

Gmail Mastodon Facebook X LinkedIn More