SHS-Net: Learning Signed Hyper Surfaces for Oriented Normal Estimation of Point Clouds

by   Qing Li, et al.

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. The code, data and pretrained models are publicly available.


page 5

page 8


HSurf-Net: Normal Estimation for 3D Point Clouds by Learning Hyper Surfaces

We propose a novel normal estimation method called HSurf-Net, which can ...

Orienting Point Clouds with Dipole Propagation

Establishing a consistent normal orientation for point clouds is a notor...

Neural Gradient Learning and Optimization for Oriented Point Normal Estimation

We propose Neural Gradient Learning (NGL), a deep learning approach to l...

Deep Point Cloud Normal Estimation via Triplet Learning

Normal estimation on 3D point clouds is a fundamental problem in 3D visi...

Deep Geometry Post-Processing for Decompressed Point Clouds

Point cloud compression plays a crucial role in reducing the huge cost o...

ActivationNet: Representation learning to predict contact quality of interacting 3-D surfaces in engineering designs

Engineering simulations for analysis of structural and fluid systems req...

Going Further with Point Pair Features

Point Pair Features is a widely used method to detect 3D objects in poin...

Please sign up or login with your details

Forgot password? Click here to reset