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.
@article{arxiv.1912.04976,
title = {Learning to Optimally Segment Point Clouds},
author = {Peiyun Hu and David Held and Deva Ramanan},
journal= {arXiv preprint arXiv:1912.04976},
year = {2019}
}