Going Further with Point Pair Features

TL;DR

This paper introduces improved sampling and voting schemes for Point Pair Features, enhancing robustness against noise and clutter, and achieving competitive performance on challenging 3D object detection benchmarks.

Contribution

It presents novel sampling and voting methods that significantly improve PPF robustness and efficiency in cluttered, noisy environments.

Findings

Outperforms state-of-the-art methods on challenging benchmarks

Reduces influence of sensor noise and background clutter

Maintains low computational cost

Abstract

Point Pair Features is a widely used method to detect 3D objects in point clouds, however they are prone to fail in presence of sensor noise and background clutter. We introduce novel sampling and voting schemes that significantly reduces the influence of clutter and sensor noise. Our experiments show that with our improvements, PPFs become competitive against state-of-the-art methods as it outperforms them on several objects from challenging benchmarks, at a low computational cost.