GSPN: Generative Shape Proposal Network for 3D Instance Segmentation in Point Cloud

Abstract

We introduce a novel 3D object proposal approach named Generative Shape Proposal Network (GSPN) for instance segmentation in point cloud data. Instead of treating object proposal as a direct bounding box regression problem, we take an analysis-by-synthesis strategy and generate proposals by reconstructing shapes from noisy observations in a scene. We incorporate GSPN into a novel 3D instance segmentation framework named Region-based PointNet (R-PointNet) which allows flexible proposal refinement and instance segmentation generation. We achieve state-of-the-art performance on several 3D instance segmentation tasks. The success of GSPN largely comes from its emphasis on geometric understandings during object proposal, which greatly reducing proposals with low objectness.

References in corpus (4)

• ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes
• Multi-View 3D Object Detection Network for Autonomous Driving
• Instance-sensitive Fully Convolutional Networks
• A Point Set Generation Network for 3D Object Reconstruction from a Single Image

Cited by in corpus (8)

• MASC: Multi-scale Affinity with Sparse Convolution for 3D Instance Segmentation
• 3D-SIS: 3D Semantic Instance Segmentation of RGB-D Scans
• PanopticFusion: Online Volumetric Semantic Mapping at the Level of Stuff and Things
• Spatial Semantic Embedding Network: Fast 3D Instance Segmentation with Deep Metric Learning
• RevealNet: Seeing Behind Objects in RGB-D Scans
• Object Segmentation of Cluttered Airborne LiDAR Point Clouds
• OccuSeg: Occupancy-aware 3D Instance Segmentation
• Multi-view PointNet for 3D Scene Understanding