Neural Gradient Learning and Optimization for Oriented Point Normal Estimation

TL;DR

This paper introduces Neural Gradient Learning with Gradient Vector Optimization, a two-phase deep learning approach for robust and accurate oriented normal estimation from 3D point clouds, outperforming previous methods.

Contribution

It presents a novel two-phase pipeline combining global gradient approximation with local refinement using an angular distance field, enhancing robustness and accuracy.

Findings

Outperforms previous methods in normal estimation accuracy.

Robust to noise, outliers, and point density variations.

Achieves state-of-the-art results on benchmark datasets.

Abstract

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 https://github.com/LeoQLi/NGLO.