Single and Cross-Dimensional Feature Detection and Description: An Evaluation

TL;DR

This paper evaluates 3D local feature detection and description techniques, highlighting the advantages of cross-dimensional methods over single-dimensional approaches in object recognition tasks.

Contribution

It provides the first comprehensive evaluation of cross-dimensional (2D and 3D) feature detection and description methods, demonstrating their superior performance.

Findings

Cross-dimensional methods outperform single-dimensional schemes.

Evaluation conducted on multiple 3D datasets.

Cross-dimensional approaches show improved accuracy in object recognition.

Abstract

Three-dimensional local feature detection and description techniques are widely used for object registration and recognition applications. Although several evaluations of 3D local feature detection and description methods have already been published, these are constrained in a single dimensional scheme, i.e. either 3D or 2D methods that are applied onto multiple projections of the 3D data. However, cross-dimensional (mixed 2D and 3D) feature detection and description has yet to be investigated. Here, we evaluated the performance of both single and cross-dimensional feature detection and description methods on several 3D datasets and demonstrated the superiority of cross-dimensional over single-dimensional schemes.