VFKD: Voxelized Fractal Keypoint Detector

In three-dimensional data, despite deep learning-based approaches achieve decent accuracy when applied to classification, they struggle on other more complex tasks such as registration. This is why traditional keypoint detection, description and matching pipelines are even currently state-of-the-art...

Full description

Saved in:
Bibliographic Details
Published in2022 International Joint Conference on Neural Networks (IJCNN) pp. 1 - 8
Main Authors Gomez-Donoso, Francisco, Escalona, Felix, Cazorla, Miguel
Format Conference Proceeding
LanguageEnglish
Published IEEE 18.07.2022
Subjects
3D Keypoint Detector
Detectors
Fractals
Machine Learning
Neural networks
Object Detection
Pattern Matching
Pipelines
Point Cloud
Registration
Task analysis
Three-dimensional displays
Online AccessGet full text

Cover

More Information
Summary:In three-dimensional data, despite deep learning-based approaches achieve decent accuracy when applied to classification, they struggle on other more complex tasks such as registration. This is why traditional keypoint detection, description and matching pipelines are even currently state-of-the-art. In this paper we propose VFKD, a Voxelized Fractal Keypoint Detector. We leverage the fractal dimension of the neighborhood of a point to either classify it as a keypoint or not. Our approach accepts a set of parameters which should be tuned for each final application, thus providing high versatility. VFKD outperforms state-of-the-art 3D keypoint extractors in terms of mean displacement error by a large margin.
ISSN:2161-4407
DOI:10.1109/IJCNN55064.2022.9892641