Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: Oct 22, 2025

Measuring the Structure, Composition, and Change of Underwater Environments with Large-area Imaging
09:19

Measuring the Structure, Composition, and Change of Underwater Environments with Large-area Imaging

Published on: April 18, 2025

944

Effective Point Cloud Analysis Using Multi-Scale Features.

Qiang Zheng1,2, Jian Sun1,2

  • 1State Key Laboratory for Strength & Vibration, School of Aerospace, Xi'an Jiaotong University, Xi'an 710049, China.

Sensors (Basel, Switzerland)
|August 28, 2021
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

A Lightweight Network for Point Cloud Analysis via the Fusion of Local Features and Distribution Characteristics.

Sensors (Basel, Switzerland)·2022
Same author

One-pot formation of chiral polysubstituted 3,4-dihydropyrans via a novel organocatalytic domino sequence involving alkynal self-condensation.

Organic letters·2012
Same author

Non-invasive microelectrode cadmium flux measurements reveal the spatial characteristics and real-time kinetics of cadmium transport in hyperaccumulator and nonhyperaccumulator ecotypes of Sedum alfredii.

Journal of plant physiology·2012
Same author

NO inhibitory guaianolide-derived terpenoids from Artemisia argyi.

Fitoterapia·2012
Same author

Rac1+ cells distributed in accordance with CD 133+ cells in glioblastomas and the elevated invasiveness of CD 133+ glioma cells with higher Rac1 activity.

Chinese medical journal·2012
Same author

Selective adsorption of Hg(II) by γ-radiation synthesized silica-graft-vinyl imidazole adsorbent.

Journal of hazardous materials·2012
Same journal

RETRACTED: Zhang et al. A Novel Framework for Reconstruction and Imaging of Target Scattering Centers via Wide-Angle Incidence in Radar Networks. <i>Sensors</i> 2025, <i>25</i>, 6802.

Sensors (Basel, Switzerland)·2026
Same journal

Enhancing Unsupervised Multi-Source Domain Adaptation for Person Re-Identification via Mixture of Experts and Graph-Based Relation.

Sensors (Basel, Switzerland)·2026
Same journal

Development of an Instrumented Glove for Palmar Pressure Assessment in Kayakers.

Sensors (Basel, Switzerland)·2026
Same journal

Development and Experimental Validation of an Autonomous IoT-Based Monitoring System for Real-Time Water Quality Assessment in the Amazon River.

Sensors (Basel, Switzerland)·2026
Same journal

Semi-Supervised Adversarial Learning Framework for Controller Area Network Bus Intrusion Detection.

Sensors (Basel, Switzerland)·2026
Same journal

Smart Optimization Method for Safety Signs in Innovative Manufacturing Environments Integrating Industrial Field IoT Sensors and Knowledge Graphs.

Sensors (Basel, Switzerland)·2026
See all related articles

This study introduces a novel, lightweight model for point cloud feature modeling, inspired by convolutional neural networks (CNNs). It effectively captures local geometric features and their spatial distributions for improved 3D shape analysis.

Area of Science:

  • Computer Vision
  • 3D Geometry Processing
  • Machine Learning

Background:

  • Analyzing local features and spatial distributions in point clouds is crucial for accurate 3D shape modeling.
  • Existing methods often struggle to efficiently capture the intricate relationships between local patterns and point coordinates.

Purpose of the Study:

  • To propose a novel, lightweight deep learning structure for point cloud feature modeling.
  • To enhance the extraction and fusion of multi-scale local features and their spatial distributions.
  • To improve the performance of 3D shape analysis tasks like classification and segmentation.

Main Methods:

  • A lightweight structure inspired by convolutional neural networks (CNNs) is proposed.
  • Multi-scale local features and their spatial distributions are extracted via parallel branches.
Keywords:
classificationdeep learningmulti-scalepart segmentationpoint cloud

More Related Videos

Use of Principal Components for Scaling Up Topographic Models to Map Soil Redistribution and Soil Organic Carbon
09:44

Use of Principal Components for Scaling Up Topographic Models to Map Soil Redistribution and Soil Organic Carbon

Published on: October 16, 2018

10.4K

Related Experiment Videos

Last Updated: Oct 22, 2025

Measuring the Structure, Composition, and Change of Underwater Environments with Large-area Imaging
09:19

Measuring the Structure, Composition, and Change of Underwater Environments with Large-area Imaging

Published on: April 18, 2025

944
Use of Principal Components for Scaling Up Topographic Models to Map Soil Redistribution and Soil Organic Carbon
09:44

Use of Principal Components for Scaling Up Topographic Models to Map Soil Redistribution and Soil Organic Carbon

Published on: October 16, 2018

10.4K
  • A two-step fusion strategy merges features on multiple levels, creating a shape-level representation.
  • Shared multi-layer perceptrons (MLPs) ensure conciseness and rapid convergence, augmented by snapshot ensemble for performance boost.

    • Main Results:

    • The proposed model generates shape-level representations rich in local characteristics and spatial relationships.
    • Experiments on classification and part segmentation tasks demonstrate competitive or superior performance compared to state-of-the-art (SOTA) methods.
    • The model's lightweight design leads to rapid convergence.

    Conclusions:

    • The novel approach effectively models correlations between local features and their spatial distribution in point clouds.
    • The proposed method offers a promising, efficient solution for 3D shape analysis.
    • The findings advance the field of point cloud processing and deep learning for 3D data.