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 10x more computationally efficient. Comprehensive ablation studies demonstrate the effectiveness of our design.
Bo Yang (University of Oxford)
Jianan Wang (DeepMind)
Ronnie Clark (Imperial College London)
Qingyong Hu (University of Oxford)
I am currently a first-year DPhil student at the University of Oxford, under the supervision of Prof. Niki Trigoni and Dr. Andrew Markham. My research interests include computer vision and machine learning.
Sen Wang (Heriot-Watt University)
Andrew Markham (University of Oxford)
Niki Trigoni (University of Oxford)
Related Events (a corresponding poster, oral, or spotlight)
2019 Spotlight: Learning Object Bounding Boxes for 3D Instance Segmentation on Point Clouds »
Wed Dec 11th 10:40 -- 10:45 AM Room West Exhibition Hall C + B3