Deep learning-based 3D local feature descriptor from Mercator projections

DOI10.1016/J.CAGD.2019.101771MaRDI QIDQ2010342zbMATH OpenOpenAlexWikidataFDO

Authors Masoumeh Rezaei, Mehdi Rezaeian, Vali Derhami, Mohammed Bennamoun, Ferdous A. Sohel

Publication date 27 November 2019

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

Full work available at URL https://researchrepository.murdoch.edu.au/id/eprint/50819/

zbMATH Keywords

deep neural networklocal descriptor3D object recognitionSiamese network

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Pattern recognition, speech recognition (68T10) Machine vision and scene understanding (68T45)

Recommendations

• Learning point cloud shapes with geometric and topological structures
• A 3D point cloud shape feature descriptor using 2D principal manifold
• Jointly learning shape descriptors and their correspondence via deep triplet CNNs
• LRC-Net: learning discriminative features on point clouds by encoding local region contexts
• Feature extraction from 3D point cloud data based on discrete curves

Cites work

• Computer Vision - ECCV 2004
• Rotational projection statistics for 3D local surface description and object recognition

Cited in

(5)

• FPFNet: Fourier transform-based point cloud filter network for point cloud learning
• Learning point cloud shapes with geometric and topological structures
• A 3D point cloud shape feature descriptor using 2D principal manifold
• LRC-Net: learning discriminative features on point clouds by encoding local region contexts
• Multi-resolution 3D CNN for learning multi-scale spatial features in CAD models

Describes a project that uses

Uses Software

• BundleFusion
• 3DFeat-Net
• FoldingNet
• 3DMatch
• PPF-FoldNet
• PPFNet
• PointNet
• TensorFlow

This page was built for publication: Deep learning-based 3D local feature descriptor from Mercator projections

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2010342)