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

61 Downloads (Pure)


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 (NIPS 2019)
PublisherNeural Information Processing Systems Foundation
Number of pages11
Publication statusAccepted/In press - 4 Sep 2019
Event2019 Conference on Neural Information Processing Systems - Vancouver, Canada
Duration: 8 Dec 201914 Dec 2019


Conference2019 Conference on Neural Information Processing Systems
Abbreviated titleNeurIPS 2019

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