Weakly Supervised Deep Functional Map for Shape Matching

TL;DR

This paper investigates the essential components of deep functional map pipelines, proposing a new weakly supervised framework that achieves state-of-the-art results in shape matching, including partial-to-full scenarios.

Contribution

It identifies minimal components for deep functional maps and introduces a novel weakly supervised framework that outperforms existing methods on benchmark datasets.

Findings

Minimal components suffice for state-of-the-art results.

The proposed framework excels in partial-to-full shape matching.

Outperforms fully supervised methods on benchmarks.

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 several benchmark datasets outperforming even the fully supervised methods by a significant margin. Our code is publicly available at https://github.com/Not-IITian/Weakly-supervised-Functional-map