Learning Object Bounding Boxes for 3D Instance Segmentation on Point Clouds

Bo Yang, Jianan Wang, Ronald Clark, Qingyong Hu, Sen Wang, Andrew Markham, Niki Trigoni

Research output: Chapter in Book/Report/Conference proceedingConference contribution

75 Downloads (Pure)

Abstract

We propose a novel, conceptually simple and general framework for instance segmentation on 3D point clouds. Our method, called 3D-BoNet, follows the simple design philosophy of per-point multilayer perceptrons (MLPs). The framework directly regresses 3D bounding boxes for all instances in a point cloud, while simultaneously predicting a point-level mask for each instance. It consists of a backbone network followed by two parallel network branches for 1) bounding box regression and 2) point mask prediction. 3D-BoNet is single-stage, anchor-free and end-to-end trainable. Moreover, it is remarkably computationally efficient as, unlike existing approaches, it does not require any post-processing steps such as non-maximum suppression, feature sampling, clustering or voting. Extensive experiments show that our approach surpasses existing work on both ScanNet and S3DIS datasets while being approximately 10× more computationally efficient. Comprehensive ablation studies demonstrate the effectiveness of our design.
Original languageEnglish
Title of host publicationAdvances in Neural Information Processing Systems 32
PublisherNeural Information Processing Systems Foundation
Pages1-10
Number of pages10
Publication statusPublished - 2019
Event33rd Conference on Neural Information Processing Systems 2019 - Vancouver, Canada
Duration: 8 Dec 201914 Dec 2019

Conference

Conference33rd Conference on Neural Information Processing Systems 2019
Abbreviated titleNeurIPS 2019
Country/TerritoryCanada
CityVancouver
Period8/12/1914/12/19

Fingerprint

Dive into the research topics of 'Learning Object Bounding Boxes for 3D Instance Segmentation on Point Clouds'. Together they form a unique fingerprint.

Cite this