Neural Gradient Learning and Optimization for Oriented Point Normal Estimation

Qing Li, Huifang Feng, Kanle Shi, Yi Fang, Yu Shen Liu, Zhizhong Han

Research output: Chapter in Book/Report/Conference proceedingConference contribution


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 .

Original languageEnglish (US)
Title of host publicationProceedings - SIGGRAPH Asia 2023 Conference Papers, SA 2023
EditorsStephen N. Spencer
PublisherAssociation for Computing Machinery, Inc
ISBN (Electronic)9798400703157
StatePublished - Dec 10 2023
Event2023 SIGGRAPH Asia 2023 Conference Papers, SA 2023 - Sydney, Australia
Duration: Dec 12 2023Dec 15 2023

Publication series

NameProceedings - SIGGRAPH Asia 2023 Conference Papers, SA 2023


Conference2023 SIGGRAPH Asia 2023 Conference Papers, SA 2023


  • Geometric Deep Learning
  • Neural Gradient
  • Normal Estimation
  • Point Clouds
  • Surface Reconstruction

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Software
  • Computer Vision and Pattern Recognition


Dive into the research topics of 'Neural Gradient Learning and Optimization for Oriented Point Normal Estimation'. Together they form a unique fingerprint.

Cite this