Joint Symmetry Detection and Shape Matching for Non-Rigid Point Cloud

TL;DR

This paper introduces a novel deep learning framework that jointly models self-symmetry and shape matching in non-rigid 3D point clouds, improving accuracy by coupling these tasks through regularization.

Contribution

It presents a new joint learning approach that simultaneously captures self-symmetry and pairwise shape correspondence, addressing symmetry mismatch issues in non-rigid shape matching.

Findings

Outperforms baseline methods on multiple benchmarks

Effectively models both symmetry and shape matching tasks

Provides more accurate non-rigid shape correspondences

Abstract

Despite the success of deep functional maps in non-rigid 3D shape matching, there exists no learning framework that models both self-symmetry and shape matching simultaneously. This is despite the fact that errors due to symmetry mismatch are a major challenge in non-rigid shape matching. In this paper, we propose a novel framework that simultaneously learns both self symmetry as well as a pairwise map between a pair of shapes. Our key idea is to couple a self symmetry map and a pairwise map through a regularization term that provides a joint constraint on both of them, thereby, leading to more accurate maps. We validate our method on several benchmarks where it outperforms many competitive baselines on both tasks.