Iterative Poisson Surface Reconstruction (iPSR) for Unoriented Points

TL;DR

The paper introduces iPSR, an iterative Poisson surface reconstruction method that reconstructs watertight surfaces from unoriented points, eliminating the need for point normals and demonstrating fast convergence and scalability.

Contribution

iPSR is a novel iterative algorithm that removes the requirement for point normals in Poisson surface reconstruction, improving robustness and efficiency.

Findings

Converges in 5-30 iterations even with random normals

Reduces iterations with a simple visibility heuristic

Outperforms existing PSR and implicit-function methods

Abstract

Poisson surface reconstruction (PSR) remains a popular technique for reconstructing watertight surfaces from 3D point samples thanks to its efficiency, simplicity, and robustness. Yet, the existing PSR method and subsequent variants work only for oriented points. This paper intends to validate that an improved PSR, called iPSR, can completely eliminate the requirement of point normals and proceed in an iterative manner. In each iteration, iPSR takes as input point samples with normals directly computed from the surface obtained in the preceding iteration, and then generates a new surface with better quality. Extensive quantitative evaluation confirms that the new iPSR algorithm converges in 5-30 iterations even with randomly initialized normals. If initialized with a simple visibility based heuristic, iPSR can further reduce the number of iterations. We conduct comprehensive comparisons with PSR and other powerful implicit-function based methods. Finally, we confirm iPSR's effectiveness and scalability on the AIM@SHAPE dataset and challenging (indoor and outdoor) scenes. Code and data for this paper are at https://github.com/houfei0801/ipsr.