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-ofthe-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.