An Improved Discriminative Optimization for 3D Rigid Point Cloud Registration

TL;DR

This paper enhances the Discriminative Optimization algorithm for 3D point cloud registration by extending feature histograms to include more spatial directions and reweighting based on point distribution, achieving comparable accuracy to state-of-the-art methods.

Contribution

The paper introduces an improved DO method with extended histograms and reweighting, enhancing feature representation for better registration performance.

Findings

Achieves comparable registration accuracy to state-of-the-art algorithms.

Demonstrates effectiveness on Stanford Bunny and Oxford SensatUrban datasets.

Reweights features based on point distribution for improved robustness.

Abstract

The Discriminative Optimization (DO) algorithm has been proved much successful in 3D point cloud registration. In the original DO, the feature (descriptor) of two point cloud was defined as a histogram, and the element of histogram indicates the weights of scene points in "front" or "back" side of a model point. In this paper, we extended the histogram which indicate the sides from "front-back" to "front-back", "up-down", and "clockwise-anticlockwise". In addition, we reweighted the extended histogram according to the model points' distribution. We evaluated the proposed Improved DO on the Stanford Bunny and Oxford SensatUrban dataset, and compared it with six classical State-Of-The-Art point cloud registration algorithms. The experimental result demonstrates our algorithm achieves comparable performance in point registration accuracy and root-mean-sqart-error.