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

NeurIPS 2019 Bo YangJianan WangRonald ClarkQingyong HuSen WangAndrew MarkhamNiki Trigoni

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)... (read more)

PDF Abstract

Evaluation Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK COMPARE
3D Instance Segmentation S3DIS 3D-BoNet mPrec 65.6% # 1
3D Instance Segmentation ScanNet(v2) 3D-BoNet Mean AP 48.8 # 1
3D Instance Segmentation ScanNet(v2) 3D-BoNet mRec 47.6 # 1