A Simple Approach to Intrinsic Correspondence Learning on Unstructured 3D Meshes

TL;DR

This paper introduces a straightforward, resampling-free method for intrinsic correspondence learning on unstructured 3D meshes, enhancing efficiency and data fidelity while achieving competitive results in shape matching tasks.

Contribution

The paper proposes a novel direct encoding approach that eliminates resampling in intrinsic correspondence learning on unstructured meshes, simplifying the process and improving data fidelity.

Findings

Achieves highly competitive shape correspondence results

Increases processing efficiency due to simplicity

Avoids data loss by eliminating resampling

Abstract

The question of representation of 3D geometry is of vital importance when it comes to leveraging the recent advances in the field of machine learning for geometry processing tasks. For common unstructured surface meshes state-of-the-art methods rely on patch-based or mapping-based techniques that introduce resampling operations in order to encode neighborhood information in a structured and regular manner. We investigate whether such resampling can be avoided, and propose a simple and direct encoding approach. It does not only increase processing efficiency due to its simplicity - its direct nature also avoids any loss in data fidelity. To evaluate the proposed method, we perform a number of experiments in the challenging domain of intrinsic, non-rigid shape correspondence estimation. In comparisons to current methods we observe that our approach is able to achieve highly competitive results.