Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

ReAgent: Point Cloud Registration using Imitation and Reinforcement Learning

About

Point cloud registration is a common step in many 3D computer vision tasks such as object pose estimation, where a 3D model is aligned to an observation. Classical registration methods generalize well to novel domains but fail when given a noisy observation or a bad initialization. Learning-based methods, in contrast, are more robust but lack in generalization capacity. We propose to consider iterative point cloud registration as a reinforcement learning task and, to this end, present a novel registration agent (ReAgent). We employ imitation learning to initialize its discrete registration policy based on a steady expert policy. Integration with policy optimization, based on our proposed alignment reward, further improves the agent's registration performance. We compare our approach to classical and learning-based registration methods on both ModelNet40 (synthetic) and ScanObjectNN (real data) and show that our ReAgent achieves state-of-the-art accuracy. The lightweight architecture of the agent, moreover, enables reduced inference time as compared to related approaches. In addition, we apply our method to the object pose estimation task on real data (LINEMOD), outperforming state-of-the-art pose refinement approaches.

Dominik Bauer, Timothy Patten, Markus Vincze• 2021

Related benchmarks

TaskDatasetResultRank
Object Pose EstimationLineMod (test)
APE97.2
18
Point cloud registrationModelNet40 categories 1-20 (held-out models)
MAE (Rotation)1.46
6
Point cloud registrationModelNet40 (categories 21-40 (held-out categories))
MAE (Rotation)1.34
6
Point cloud registrationScanObjectNN Segmented Objects (test)
MAE R0.77
6
Showing 4 of 4 rows

Other info

Code

Follow for update