Multi-resolution 3D CNN for learning multi-scale spatial features in CAD models

DOI10.1016/J.CAGD.2021.102038zbMATH Open1480.65055OpenAlexW3204631764MaRDI QIDQ2065636FDOQ2065636

Authors: Sambit Ghadai, Xian Yeow Lee, Aditya Balu, Soumik Sarkar, Adarsh Krishnamurthy 

Publication date: 12 January 2022

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

Full work available at URL: https://doi.org/10.1016/j.cagd.2021.102038

Recommendations

• Learning point cloud shapes with geometric and topological structures
• Multi-scale mesh saliency based on low-rank and sparse analysis in shape feature space
• Deep learning-based 3D local feature descriptor from Mercator projections
• 3D object modeling and recognition using local affine-invariant image descriptors and multi-view spatial constraints
• A multiresolutional approach to 3D object recognition

zbMATH Keywords

deep learninginterpretabilityobject recognitionmulti-level voxel representationmulti-resolution CNN

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Numerical aspects of computer graphics, image analysis, and computational geometry (65D18)

Cites Work

• Title not available (Why is that?)
• Graph-based heuristics for recognition of machined features from a 3D solid model
• Learning localized features in 3D CAD models for manufacturability analysis of drilled holes

Cited In (2)

• Learning localized features in 3D CAD models for manufacturability analysis of drilled holes
• D3AdvM: A direct 3D adversarial sample attack inside mesh data

Uses Software

• DiffSharp
• ImageNet
• PointNet
• Grad-CAM
• OctNet
• VoxNet
• AlexNet
• PyG
• MinkowskiEngine

This page was built for publication: Multi-resolution 3D CNN for learning multi-scale spatial features in CAD models

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2065636)