Learning Modified Indicator Functions for Surface Reconstruction

TL;DR

This paper introduces a learning-based method for implicit surface reconstruction from raw point clouds, utilizing a novel neural network inspired by potential energy theory to produce smooth, high-quality surfaces.

Contribution

It presents a new neural network architecture that learns modified indicator functions directly from un-oriented, noisy point clouds for improved surface reconstruction.

Findings

Achieves state-of-the-art reconstruction accuracy.

Produces smooth surfaces with high normal consistency.

Effectively handles noisy point cloud data.

Abstract

Surface reconstruction is a fundamental problem in 3D graphics. In this paper, we propose a learning-based approach for implicit surface reconstruction from raw point clouds without normals. Our method is inspired by Gauss Lemma in potential energy theory, which gives an explicit integral formula for the indicator functions. We design a novel deep neural network to perform surface integral and learn the modified indicator functions from un-oriented and noisy point clouds. We concatenate features with different scales for accurate point-wise contributions to the integral. Moreover, we propose a novel Surface Element Feature Extractor to learn local shape properties. Experiments show that our method generates smooth surfaces with high normal consistency from point clouds with different noise scales and achieves state-of-the-art reconstruction performance compared with current data-driven and non-data-driven approaches.