Learning to Optimally Segment Point Clouds

TL;DR

This paper introduces a novel method for class-agnostic segmentation of LiDAR point clouds that combines graph search with data-driven scoring, achieving superior results over previous approaches.

Contribution

It presents a new algorithm that efficiently finds optimal segmentations based on objectness scores, with proven worst-case and average-case performance guarantees.

Findings

Outperforms previous bottom-up segmentation methods

Efficient algorithms for optimal segmentation

Validated on KITTI dataset with superior results

Abstract

We focus on the problem of class-agnostic instance segmentation of LiDAR point clouds. We propose an approach that combines graph-theoretic search with data-driven learning: it searches over a set of candidate segmentations and returns one where individual segments score well according to a data-driven point-based model of "objectness". We prove that if we score a segmentation by the worst objectness among its individual segments, there is an efficient algorithm that finds the optimal worst-case segmentation among an exponentially large number of candidate segmentations. We also present an efficient algorithm for the average-case. For evaluation, we repurpose KITTI 3D detection as a segmentation benchmark and empirically demonstrate that our algorithms significantly outperform past bottom-up segmentation approaches and top-down object-based algorithms on segmenting point clouds.