Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Selected Data About Geographic Locations

Selected Data About Geographic Locations

Geographic Information Systems (GIS) rely on two core types of data: spatial data and attribute data.Spatial DataSpatial data defines the physical location of features within a coordinate system, typically expressed in terms of latitude and longitude. It provides precise positioning for elements like roads, rivers, or buildings.Attribute DataAttribute data complements spatial data by adding descriptive information about these features. For example, a road's spatial data includes its start and...

You might also read

Related Articles

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

Sort by

Same author

Clinical response and risk factors of fecal microbiota transplantation in children: a systematic review and meta-analysis.

European journal of pediatrics·2026

Same author

Esketamine and postoperative cognitive dysfunction in aged mice: Role of the SIRT3/AMPK/mTOR pathway.

Pakistan journal of pharmaceutical sciences·2026

Same author

Is Fusion 360 Reconstruction Dataset Really Not Enough for Training When Compared With DeepCAD Dataset?

IEEE computer graphics and applications·2026

Same author

CADRec-Net: Reconstruct CAD Design From B-Rep to Support Reuse and Redesign.

IEEE computer graphics and applications·2026

Same author

The correlation of umbilical cord blood quality and placental function with neonatal outcomes in fetal growth restriction.

Frontiers in medicine·2026

Same author

Personalized tumor-informed circulating tumor DNA monitoring for early detection of recurrence in postoperative pancreatic cancer.

Frontiers in oncology·2026

Search research articles

Related Experiment Video

Updated: Sep 10, 2025

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

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

Published on: April 18, 2025

Adaptive spatial feature extraction and graphical feature awareness for robust point cloud registration.

Yilin Chen¹, Yang Mei², Tao Lu¹

¹School of Computer Science and Engineering, Wuhan Institute of Technology, Wuhan, 430073, China; Hubei Key Laboratory of Intelligent Robot, Wuhan Institute of Technology, Wuhan, 430073, China.

Neural Networks : the Official Journal of the International Neural Network Society

|August 21, 2025

Summary

This summary is machine-generated.

This study introduces LDGR, a novel method for 3D point cloud registration. LDGR enhances feature extraction and uses a new evaluation approach for robust performance, especially in low-overlap scenarios, reducing computational costs.

Keywords:

Feature extraction Feature matching Point cloud registration Transformer

More Related Videos

Photorealistic Learned Landscapes for Augmented Reality

Photorealistic Learned Landscapes for Augmented Reality

Published on: June 27, 2025

Author Spotlight: Revolutionizing Remote Surgery with Augmented Reality and Robotics for Enhanced Precision and Accessibility

Author Spotlight: Revolutionizing Remote Surgery with Augmented Reality and Robotics for Enhanced Precision and Accessibility

Published on: August 9, 2024

Related Experiment Videos

Last Updated: Sep 10, 2025

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

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

Published on: April 18, 2025

Photorealistic Learned Landscapes for Augmented Reality

Photorealistic Learned Landscapes for Augmented Reality

Published on: June 27, 2025

Author Spotlight: Revolutionizing Remote Surgery with Augmented Reality and Robotics for Enhanced Precision and Accessibility

Author Spotlight: Revolutionizing Remote Surgery with Augmented Reality and Robotics for Enhanced Precision and Accessibility

Published on: August 9, 2024

Area of Science:

Computer Vision
3D Point Cloud Processing
Machine Learning

Background:

Transformers excel in 3D vision but struggle with low-overlap point cloud registration due to ineffective attention.
Existing RANSAC methods require extensive iterations, leading to high computational costs.

Purpose of the Study:

To develop a robust point cloud registration method for low-overlap scenarios.
To reduce the computational overhead associated with traditional registration techniques.

Main Methods:

Introduced Adaptive Point Convolution (APConv) for feature extraction with adaptive receptive fields.
Enhanced Transformers with local geometric information and graphical awareness for improved low-overlap performance.
Proposed a Local Diffusion to Global (LDGR) registration evaluator, reducing iterative computations.

Main Results:

Achieved optimal results on ModelNet and ModelLoNet datasets, outperforming state-of-the-art methods.
Demonstrated robustness on 3DMatch and 3DLoMatch datasets with a substantially higher inlier ratio.
Showed comparable performance to RANSAC on the KITTI dataset with significantly fewer iterations.

Conclusions:

LDGR offers a robust and computationally efficient solution for 3D point cloud registration, particularly in challenging low-overlap conditions.
The proposed APConv and LDGR evaluator contribute to improved feature extraction and registration accuracy.