PointDifformer: Robust Point Cloud Registration With Neural Diffusion and Transformer

arXiv:2404.14034v1 Announce Type: new
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 …

3-d abstract applications arxiv autonomous autonomous driving cloud computer computer vision cs.cv diffusion driving fundamental graphics however noise registration robotics robust tasks transformer type vision