GSPN: Generative Shape Proposal Network for 3D Instance Segmentation in Point Cloud
This addresses 3D instance segmentation for point cloud data, offering a novel approach with strong performance gains.
The paper tackles 3D instance segmentation in point clouds by introducing GSPN, a generative shape proposal network that reconstructs shapes from noisy observations, achieving state-of-the-art performance on several tasks.
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.