Learning Signed Hyper Surfaces for Oriented Point Cloud Normal Estimation

TL;DR

SHS-Net is a novel end-to-end deep learning method that accurately estimates globally consistent oriented normals from point clouds by learning signed hyper surfaces, outperforming existing approaches especially in noisy and complex scenarios.

Contribution

Introduces SHS-Net, a new approach that learns signed hyper surfaces for end-to-end oriented normal estimation from point clouds, integrating local and global features with attention mechanisms.

Findings

Outperforms state-of-the-art methods on benchmark datasets.

Robust to noise, density variations, and complex geometries.

Provides accurate and globally consistent normal estimations.

Abstract

We propose a novel method called SHS-Net for oriented normal estimation of point clouds by learning signed hyper surfaces, which can accurately predict normals with global consistent orientation from various point clouds. Almost all existing methods estimate oriented normals through a two-stage pipeline, i.e., unoriented normal estimation and normal orientation, and each step is implemented by a separate algorithm. However, previous methods are sensitive to parameter settings, resulting in poor results from point clouds with noise, density variations and complex geometries. In this work, we introduce signed hyper surfaces (SHS), which are parameterized by multi-layer perceptron (MLP) layers, to learn to estimate oriented normals from point clouds in an end-to-end manner. The signed hyper surfaces are implicitly learned in a high-dimensional feature space where the local and global information is aggregated. Specifically, we introduce a patch encoding module and a shape encoding module to encode a 3D point cloud into a local latent code and a global latent code, respectively. Then, an attention-weighted normal prediction module is proposed as a decoder, which takes the local and global latent codes as input to predict oriented normals. Experimental results show that our SHS-Net outperforms the state-of-the-art methods in both unoriented and oriented normal estimation on the widely used benchmarks.