Systems and methods for semantic segmentation of 3D point clouds

US11004202B2 · kind B2 · utility

Assignee

• The Board of Trustees of the Leland Stanford Junior University · US

Inventors

• Lyne P. Tchapmi · Stanford, US
• Christopher Bongsoo Choy · Los Angeles, US
• Iro Armeni · Stanford, US
• JunYoung Gwak · Stanford, US
• Silvio Savarese · Palo Alto, US

Key dates

• Filing date: Oct 9, 2018
• Grant date: May 11, 2021
• Expiry date: Apr 28, 2039

Classification

• Technology area (CPC G): Physics
• CPC primary: G06V2201/12
• WIPO field: Computer technology
• WIPO sector: Electrical engineering

Abstract

Systems and methods for obtaining 3D point-level segmentation of 3D point clouds in accordance with various embodiments of the invention are disclosed. One embodiment includes: at least one processor, and a memory containing a segmentation pipeline application. In addition, the segmentation pipeline application configures the at least one processor to: pre-process a 3D point cloud to group 3D points; provide the groups of 3D points to a 3D neural network to generate initial label predictions for the groups of 3D points; interpolate label predictions for individual 3D points based upon initial label predictions for at least two neighboring groups of 3D points including the group of 3D points to which a given individual 3D point belongs; refine the label predictions using a graph neural network; and output a segmented 3D point cloud.