Multi-Model 3D Registration: Finding Multiple Moving Objects in Cluttered Point Clouds

We investigate a variation of the 3D registration problem, named multi-model 3D registration. In the multi-model registration problem, we are given two point clouds picturing a set of objects at different poses (and possibly including points belonging to the background) and we want to simultaneously reconstruct how all objects moved between the two point clouds. This setup generalizes standard 3D registration where one wants to reconstruct a single pose, e. g. , the motion of the sensor picturing a static scene. Moreover, it provides a mathematically grounded formulation for relevant robotics applications, e. g. , where a depth sensor onboard a robot perceives a dynamic scene and has the goal of estimating its own motion (from the static portion of the scene) while simultaneously recovering the motion of all dynamic objects. We assume a correspondence-based setup where we have putative matches between the two point clouds and consider the practical case where these correspondences are plagued with outliers. We then propose a simple approach based on Expectation-Maximization (EM) and establish theoretical conditions under which the EM approach converges to the ground truth. We evaluate the approach in simulated and real datasets ranging from table-top scenes to self-driving scenarios and demonstrate its effectiveness when combined with state-of-the-art scene flow methods to establish dense correspondences.

Authors

• David Jin
• Sushrut Karmalkar
• Harry Zhang
• Luca Carlone

Keywords

• Point cloud compression
• Three-dimensional displays
• Dynamics
• Robot sensing systems
• Distance measurement
• Standards
• Point Cloud
• Object Motion
• 3D Registration
• Expectation Maximization
• Variant Of Problem
• Registration Problem
• Intersection Over Union
• Nonlinear Least Squares
• RGB Images
• Optical Flow
• Pair Of Points
• Pose Estimation
• Rigid Transformation
• Translation Error
• Pair Of Clusters
• Inliers
• Rotation Error
• Object Pose
• Good Clustering
• Problem In Robotics
• Robust Registration
• Disparity Map
• Ground Truth Pose
• Ground Truth Object
• Noiseless Case
• Intersection Over Union Score
• Object Point Cloud
• Singular Value Decomposition
• Computer Vision
• Number Of Objects