PointDifformer: Robust Point Cloud Registration With Neural Diffusion and Transformer

TL;DR

PointDifformer introduces a robust point cloud registration method combining graph neural PDEs and heat kernel signatures, achieving state-of-the-art accuracy and noise robustness in 3D registration tasks.

Contribution

The paper presents a novel neural diffusion and transformer-based approach that enhances robustness and accuracy in point cloud registration under challenging conditions.

Findings

Achieves state-of-the-art registration performance.

Demonstrates superior robustness to noise and perturbations.

Effective feature extraction using graph neural PDEs and heat kernel signatures.

Abstract

Point cloud registration is a fundamental technique in 3-D computer vision with applications in graphics, autonomous driving, and robotics. However, registration tasks under challenging conditions, under which noise or perturbations are prevalent, can be difficult. We propose a robust point cloud registration approach that leverages graph neural partial differential equations (PDEs) and heat kernel signatures. Our method first uses graph neural PDE modules to extract high dimensional features from point clouds by aggregating information from the 3-D point neighborhood, thereby enhancing the robustness of the feature representations. Then, we incorporate heat kernel signatures into an attention mechanism to efficiently obtain corresponding keypoints. Finally, a singular value decomposition (SVD) module with learnable weights is used to predict the transformation between two point clouds. Empirical experiments on a 3-D point cloud dataset demonstrate that our approach not only achieves state-of-the-art performance for point cloud registration but also exhibits better robustness to additive noise or 3-D shape perturbations.