# ReAgent: Point Cloud Registration using Imitation and Reinforcement Learning

arXiv: https://arxiv.org/abs/2103.15231 · HTML: https://mlsanity.com/paper/2103.15231/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 41 references that are in the map.
- First posted on arXiv 28 Mar 2021.

## Builds on (most cited first, 26 of 26)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [High-Dimensional Continuous Control Using Generalized Advantage Estimation](https://mlsanity.com/paper/1506.02438/) (2015)
- [On the Convergence of Adam and Beyond](https://mlsanity.com/paper/1904.09237/) (2019)
- [PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenes](https://mlsanity.com/paper/1711.00199/) (2017)
- [Open3D: A Modern Library for 3D Data Processing](https://mlsanity.com/paper/1801.09847/) (2018)
- [Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Data](https://mlsanity.com/paper/1908.04616/) (2019)
- [DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusion](https://mlsanity.com/paper/1901.04780/) (2019)
- [Deep Closest Point: Learning Representations for Point Cloud Registration](https://mlsanity.com/paper/1905.03304/) (2019)
- [DeepIM: Deep Iterative Matching for 6D Pose Estimation](https://mlsanity.com/paper/1804.00175/) (2018)
- [TEASER: Fast and Certifiable Point Cloud Registration](https://mlsanity.com/paper/2001.07715/) (2020)
- [PointNetLK: Robust & Efficient Point Cloud Registration using PointNet](https://mlsanity.com/paper/1903.05711/) (2019)
- [Deep Global Registration](https://mlsanity.com/paper/2004.11540/) (2020)
- [BB8: A Scalable, Accurate, Robust to Partial Occlusion Method for Predicting the 3D Poses of Challenging Objects without Using Depth](https://mlsanity.com/paper/1703.10896/) (2017)
- [Real-Time Seamless Single Shot 6D Object Pose Prediction](https://mlsanity.com/paper/1711.08848/) (2017)
- [DPOD: 6D Pose Object Detector and Refiner](https://mlsanity.com/paper/1902.11020/) (2019)
- [RPM-Net: Robust Point Matching using Learned Features](https://mlsanity.com/paper/2003.13479/) (2020)
- [Go-ICP: A Globally Optimal Solution to 3D ICP Point-Set Registration](https://mlsanity.com/paper/1605.03344/) (2016)
- [PRNet: Self-Supervised Learning for Partial-to-Partial Registration](https://mlsanity.com/paper/1910.12240/) (2019)
- [I Like to Move It: 6D Pose Estimation as an Action Decision Process](https://mlsanity.com/paper/2009.12678/) (2020)
- [PFRL: Pose-Free Reinforcement Learning for 6D Pose Estimation](https://mlsanity.com/paper/2102.12096/) (2021)
- [PoseAgent: Budget-Constrained 6D Object Pose Estimation via Reinforcement Learning](https://mlsanity.com/paper/1612.03779/) (2016)
- [One Framework to Register Them All: PointNet Encoding for Point Cloud Alignment](https://mlsanity.com/paper/1912.05766/) (2019)
- [Augmenting GAIL with BC for sample efficient imitation learning](https://mlsanity.com/paper/2001.07798/) (2020)
- [PointNetLK Revisited](https://mlsanity.com/paper/2008.09527/) (2020)

## Built on by (most cited first, 23 of 23)

- [GenDP: 3D Semantic Fields for Category-Level Generalizable Diffusion Policy](https://mlsanity.com/paper/2410.17488/) (2024)
- [Sampling Network Guided Cross-Entropy Method for Unsupervised Point Cloud Registration](https://mlsanity.com/paper/2109.06619/) (2021)
- [Challenges for Monocular 6D Object Pose Estimation in Robotics](https://mlsanity.com/paper/2307.12172/) (2023)
- [Reliable Inlier Evaluation for Unsupervised Point Cloud Registration](https://mlsanity.com/paper/2202.11292/) (2022)
- [P3-PO: Prescriptive Point Priors for Visuo-Spatial Generalization of Robot Policies](https://mlsanity.com/paper/2412.06784/) (2024)
- [ARCS: Accurate Rotation and Correspondence Search](https://mlsanity.com/paper/2203.14493/) (2022)
- [Robust Partial-to-Partial Point Cloud Registration in a Full Range](https://mlsanity.com/paper/2111.15606/) (2021)
- [Coarse-to-Fine Point Cloud Registration with SE(3)-Equivariant Representations](https://mlsanity.com/paper/2210.02045/) (2022)
- [Full Transformer Framework for Robust Point Cloud Registration with Deep Information Interaction](https://mlsanity.com/paper/2112.09385/) (2021)
- [ArchGym: An Open-Source Gymnasium for Machine Learning Assisted Architecture Design](https://mlsanity.com/paper/2306.08888/) (2023)
- [SporeAgent: Reinforced Scene-level Plausibility for Object Pose Refinement](https://mlsanity.com/paper/2201.00239/) (2022)
- [Robust-DefReg: A Robust Deformable Point Cloud Registration Method based on Graph Convolutional Neural Networks](https://mlsanity.com/paper/2306.04701/) (2023)
- [CMR-Agent: Learning a Cross-Modal Agent for Iterative Image-to-Point Cloud Registration](https://mlsanity.com/paper/2408.02394/) (2024)
- [Point Cloud Registration-Driven Robust Feature Matching for 3D Siamese Object Tracking](https://mlsanity.com/paper/2209.06395/) (2022)
- [Cut-and-Approximate: 3D Shape Reconstruction from Planar Cross-sections with Deep Reinforcement Learning](https://mlsanity.com/paper/2210.12509/) (2022)
- [Open Challenges for Monocular Single-shot 6D Object Pose Estimation](https://mlsanity.com/paper/2302.11827/) (2023)
- [DefTransNet: A Transformer-based Method for Non-Rigid Point Cloud Registration in the Simulation of Soft Tissue Deformation](https://mlsanity.com/paper/2502.06336/) (2025)
- [Lucida: Parse, Generate, and Place for Composable Real-to-Sim Scene Modeling](https://mlsanity.com/paper/2608.30821/) (2026)
- [TrackAgent: 6D Object Tracking via Reinforcement Learning](https://mlsanity.com/paper/2307.15671/) (2023)
- [Correspondence-Free Fast and Robust Spherical Point Pattern Registration](https://mlsanity.com/paper/2508.02339/) (2025)
- [PRANet: Point Cloud Registration with an Artificial Agent](https://mlsanity.com/paper/2109.11349/) (2021)
- [One-Nearest Neighborhood Guides Inlier Estimation for Unsupervised Point Cloud Registration](https://mlsanity.com/paper/2307.14019/) (2023)
- [SynBench: A Synthetic Benchmark for Non-rigid 3D Point Cloud Registration](https://mlsanity.com/paper/2409.14474/) (2024)

## Abstract (arXiv)

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.