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

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 CVPR 2018 PDF CVPR 2018 Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Instance Segmentation NYU Depth v2 SGPN-CNN mAP@0.5 30.5 # 1
3D Object Detection NYU Depth v2 SGPN-CNN MAP 41.3 # 1
3D Semantic Instance Segmentation ScanNetV1 SGPN mAP@0.25 35.1 # 1
3D Semantic Instance Segmentation ScanNetV2 SGPN mAP@0.50 14.3 # 5
3D Object Detection ScanNetV2 SGPN mAP@0.25 20.7 # 8
Semantic Segmentation ShapeNet SGPN Mean IoU 85.8% # 1
3D Part Segmentation ShapeNet-Part SGPN Class Average IoU 82.8 # 10
Instance Average IoU 85.8 # 11

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet