SGPN: Similarity Group Proposal Network for 3D Point Cloud Instance Segmentation

CVPR 2018 Weiyue WangRonald YuQiangui HuangUlrich Neumann

We introduce Similarity Group Proposal Network (SGPN), a simple and intuitive deep learning framework for 3D object instance segmentation on point clouds. SGPN uses a single network to predict point grouping proposals and a corresponding semantic class for each proposal, from which we can directly extract instance segmentation results... (read more)

PDF Abstract

Evaluation results from the paper

Task Dataset Model Metric name Metric value Global rank Compare
3D Object Detection NYU Depth v2 SGPN-CNN MAP 41.30 # 1
Instance Segmentation NYU Depth v2 SGPN-CNN MAP 43.5 # 1
3D Semantic Instance Segmentation ScanNetV1 SGPN [email protected] 35.1 # 1
3D Semantic Instance Segmentation ScanNetV2 SGPN [email protected] 14.3 # 2
Semantic Segmentation ShapeNet SGPN Mean IoU 85.8% # 1