English

3D-BEVIS: Bird's-Eye-View Instance Segmentation

Computer Vision and Pattern Recognition 2019-12-20 v3

Abstract

Recent deep learning models achieve impressive results on 3D scene analysis tasks by operating directly on unstructured point clouds. A lot of progress was made in the field of object classification and semantic segmentation. However, the task of instance segmentation is less explored. In this work, we present 3D-BEVIS, a deep learning framework for 3D semantic instance segmentation on point clouds. Following the idea of previous proposal-free instance segmentation approaches, our model learns a feature embedding and groups the obtained feature space into semantic instances. Current point-based methods scale linearly with the number of points by processing local sub-parts of a scene individually. However, to perform instance segmentation by clustering, globally consistent features are required. Therefore, we propose to combine local point geometry with global context information from an intermediate bird's-eye view representation.

Keywords

Cite

@article{arxiv.1904.02199,
  title  = {3D-BEVIS: Bird's-Eye-View Instance Segmentation},
  author = {Cathrin Elich and Francis Engelmann and Theodora Kontogianni and Bastian Leibe},
  journal= {arXiv preprint arXiv:1904.02199},
  year   = {2019}
}

Comments

camera-ready version for GCPR '19

R2 v1 2026-06-23T08:28:35.103Z