GeoHI-GNN: geometry-aware hierarchical graph representation learning for normal estimation

DOI10.1016/J.CAGD.2024.102390MaRDI QIDQ6635663zbMATH OpenFDO

Authors Nannan Li, Xin-yuan Li, Jun Zhou, Dong Jiang, Jian Liu, Hong Qin

Publication date 12 November 2024

Published in Computer Aided Geometric Design (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/J.CAGD.2024.102390

zbMATH Keywords

3D deep learningdynamic graph convolutionhierarchical graphsnormal estimationrepresentation learningsurface fitting

Mathematics Subject Classification ID

Computer-aided design (modeling of curves and surfaces) (65D17) Artificial neural networks and deep learning (68T07)

Recommendations

• Normal estimation via shifted neighborhood for point cloud
• Learning point cloud shapes with geometric and topological structures
• Point Cloud Segmentation and Denoising via Constrained Nonlinear Least Squares Normal Estimates
• Normal estimation on manifolds by gradient learning.
• Point cloud normal estimation based on neighborhood drift

Cites work

• Estimating differential quantities using polynomial fitting of osculating jets
• Provable surface reconstruction from noisy samples
• Robust regression using iteratively reweighted least-squares

This page was built for publication: GeoHI-GNN: geometry-aware hierarchical graph representation learning for normal estimation

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6635663)