Learning Signed Hyper Surfaces for Oriented Point Cloud Normal Estimation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Qing, Feng, Huifang, Shi, Kanle, Gao, Yue, Fang, Yi, Liu, Yu-Shen, Han, Zhizhong
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916338970132480
author Li, Qing
Feng, Huifang
Shi, Kanle
Gao, Yue
Fang, Yi
Liu, Yu-Shen
Han, Zhizhong
author_facet Li, Qing
Feng, Huifang
Shi, Kanle
Gao, Yue
Fang, Yi
Liu, Yu-Shen
Han, Zhizhong
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2305_05873
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Learning Signed Hyper Surfaces for Oriented Point Cloud Normal Estimation
Li, Qing
Feng, Huifang
Shi, Kanle
Gao, Yue
Fang, Yi
Liu, Yu-Shen
Han, Zhizhong
Computer Vision and Pattern Recognition
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.
title Learning Signed Hyper Surfaces for Oriented Point Cloud Normal Estimation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2305.05873