Neural Gradient Learning and Optimization for Oriented Point Normal Estimation

by   Qing Li, et al.

We propose Neural Gradient Learning (NGL), a deep learning approach to learn gradient vectors with consistent orientation from 3D point clouds for normal estimation. It has excellent gradient approximation properties for the underlying geometry of the data. We utilize a simple neural network to parameterize the objective function to produce gradients at points using a global implicit representation. However, the derived gradients usually drift away from the ground-truth oriented normals due to the lack of local detail descriptions. Therefore, we introduce Gradient Vector Optimization (GVO) to learn an angular distance field based on local plane geometry to refine the coarse gradient vectors. Finally, we formulate our method with a two-phase pipeline of coarse estimation followed by refinement. Moreover, we integrate two weighting functions, i.e., anisotropic kernel and inlier score, into the optimization to improve the robust and detail-preserving performance. Our method efficiently conducts global gradient approximation while achieving better accuracy and generalization ability of local feature description. This leads to a state-of-the-art normal estimator that is robust to noise, outliers and point density variations. Extensive evaluations show that our method outperforms previous works in both unoriented and oriented normal estimation on widely used benchmarks. The source code and pre-trained models are available at


page 7

page 12

page 14

page 15

page 17

page 18

page 19

page 20


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

We propose a novel method called SHS-Net for oriented normal estimation ...

DiGS : Divergence guided shape implicit neural representation for unoriented point clouds

Neural shape representations have recently shown to be effective in shap...

Orienting Point Clouds with Dipole Propagation

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

GraphFit: Learning Multi-scale Graph-Convolutional Representation for Point Cloud Normal Estimation

We propose a precise and efficient normal estimation method that can dea...

NeAF: Learning Neural Angle Fields for Point Normal Estimation

Normal estimation for unstructured point clouds is an important task in ...

Depth Completion using Geometry-Aware Embedding

Exploiting internal spatial geometric constraints of sparse LiDARs is be...

Graph-theoretical approach to robust 3D normal extraction of LiDAR data

Low dimensional primitive feature extraction from LiDAR point clouds (su...

Please sign up or login with your details

Forgot password? Click here to reset