Anisotropic Gauss Reconstruction for Unoriented Point Clouds

TL;DR

This paper introduces an anisotropic Gauss reconstruction method for unoriented point clouds, enhancing surface reconstruction by leveraging anisotropic information and adaptive strategies, leading to improved handling of thin structures and small holes.

Contribution

It proposes a novel anisotropic formulation with a convection term in the Laplace operator and an adaptive velocity vector strategy for better surface reconstruction.

Findings

Achieves state-of-the-art reconstruction quality.

Effectively handles thin structures and small holes.

Outperforms existing isotropic methods.

Abstract

Unoriented surface reconstructions based on the Gauss formula have attracted much attention due to their elegant mathematical formulation and excellent performance. However, the isotropic characteristics of the formulation limit their capacity to leverage the anisotropic information within the point cloud. In this work, we propose a novel anisotropic formulation by introducing a convection term in the original Laplace operator. By choosing different velocity vectors, the anisotropic feature can be exploited to construct more effective linear equations. Moreover, an adaptive selection strategy is introduced for the velocity vector to further enhance the orientation and reconstruction performance of thin structures. Extensive experiments demonstrate that our method achieves state-of-the-art performance and manages various challenging situations, especially for models with thin structures or small holes. The source code will be released on GitHub.