# Sampling Network Guided Cross-Entropy Method for Unsupervised Point Cloud Registration

arXiv: https://arxiv.org/abs/2109.06619 · HTML: https://mlsanity.com/paper/2109.06619/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 63 references that are in the map.
- First posted on arXiv 14 Sep 2021.

## Builds on (most cited first, 24 of 24)

- [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)
- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [Dream to Control: Learning Behaviors by Latent Imagination](https://mlsanity.com/paper/1912.01603/) (2019)
- [Learning Latent Dynamics for Planning from Pixels](https://mlsanity.com/paper/1811.04551/) (2018)
- [From Softmax to Sparsemax: A Sparse Model of Attention and Multi-Label Classification](https://mlsanity.com/paper/1602.02068/) (2016)
- [Deep Closest Point: Learning Representations for Point Cloud Registration](https://mlsanity.com/paper/1905.03304/) (2019)
- [Deep Global Registration](https://mlsanity.com/paper/2004.11540/) (2020)
- [RPM-Net: Robust Point Matching using Learned Features](https://mlsanity.com/paper/2003.13479/) (2020)
- [PPFNet: Global Context Aware Local Features for Robust 3D Point Matching](https://mlsanity.com/paper/1802.02669/) (2018)
- [PRNet: Self-Supervised Learning for Partial-to-Partial Registration](https://mlsanity.com/paper/1910.12240/) (2019)
- [Feature-metric Registration: A Fast Semi-supervised Approach for Robust Point Cloud Registration without Correspondences](https://mlsanity.com/paper/2005.01014/) (2020)
- [3DRegNet: A Deep Neural Network for 3D Point Registration](https://mlsanity.com/paper/1904.01701/) (2019)
- [DeepGMR: Learning Latent Gaussian Mixture Models for Registration](https://mlsanity.com/paper/2008.09088/) (2020)
- [IMLS-SLAM: scan-to-model matching based on 3D data](https://mlsanity.com/paper/1802.08633/) (2018)
- [The Differentiable Cross-Entropy Method](https://mlsanity.com/paper/1909.12830/) (2019)
- [SDRSAC: Semidefinite-Based Randomized Approach for Robust Point Cloud Registration without Correspondences](https://mlsanity.com/paper/1904.03483/) (2019)
- [Unsupervised cycle-consistent deformation for shape matching](https://mlsanity.com/paper/1907.03165/) (2019)
- [ReAgent: Point Cloud Registration using Imitation and Reinforcement Learning](https://mlsanity.com/paper/2103.15231/) (2021)
- [Mapping in a cycle: Sinkhorn regularized unsupervised learning for point cloud shapes](https://mlsanity.com/paper/2007.09594/) (2020)
- [Unsupervised Learning of 3D Point Set Registration](https://mlsanity.com/paper/2006.06200/) (2020)
- [Planning with Learned Dynamic Model for Unsupervised Point Cloud Registration](https://mlsanity.com/paper/2108.02613/) (2021)
- [Unsupervised Partial Point Set Registration via Joint Shape Completion and Registration](https://mlsanity.com/paper/2009.05290/) (2020)
- [On-device Scalable Image-based Localization via Prioritized Cascade Search and Fast One-Many RANSAC](https://mlsanity.com/paper/1802.03510/) (2018)

## Built on by (most cited first, 24 of 24)

- [Unsupervised Point Cloud Representation Learning with Deep Neural Networks: A Survey](https://mlsanity.com/paper/2202.13589/) (2022)
- [SE(3) Diffusion Model-based Point Cloud Registration for Robust 6D Object Pose Estimation](https://mlsanity.com/paper/2310.17359/) (2023)
- [Robust Outlier Rejection for 3D Registration with Variational Bayes](https://mlsanity.com/paper/2304.01514/) (2023)
- [Unsupervised Deep Probabilistic Approach for Partial Point Cloud Registration](https://mlsanity.com/paper/2303.13290/) (2023)
- [Reliable Inlier Evaluation for Unsupervised Point Cloud Registration](https://mlsanity.com/paper/2202.11292/) (2022)
- [SPAZER: Spatial-Semantic Progressive Reasoning Agent for Zero-shot 3D Visual Grounding](https://mlsanity.com/paper/2506.21924/) (2025)
- [Robust Partial-to-Partial Point Cloud Registration in a Full Range](https://mlsanity.com/paper/2111.15606/) (2021)
- [UTOPIC: Uncertainty-aware Overlap Prediction Network for Partial Point Cloud Registration](https://mlsanity.com/paper/2208.02712/) (2022)
- [VGGT-360: Geometry-Consistent Zero-Shot Panoramic Depth Estimation](https://mlsanity.com/paper/2603.18943/) (2026)
- [Novel class discovery meets foundation models for 3D semantic segmentation](https://mlsanity.com/paper/2312.03782/) (2023)
- [Category-Level Global Camera Pose Estimation with Multi-Hypothesis Point Cloud Correspondences](https://mlsanity.com/paper/2209.14419/) (2022)
- [FUSER: Feed-Forward MUltiview 3D Registration Transformer and SE(3)N Diffusion Refinement](https://mlsanity.com/paper/2512.09373/) (2025)
- [Point Cloud Registration-Driven Robust Feature Matching for 3D Siamese Object Tracking](https://mlsanity.com/paper/2209.06395/) (2022)
- [Graph Matching Optimization Network for Point Cloud Registration](https://mlsanity.com/paper/2302.05844/) (2023)
- [3D Surface Reconstruction in the Wild by Deforming Shape Priors from Synthetic Data](https://mlsanity.com/paper/2302.12883/) (2023)
- [Overlap Bias Matching is Necessary for Point Cloud Registration](https://mlsanity.com/paper/2308.09364/) (2023)
- [3D Registration in 30 Years: A Survey](https://mlsanity.com/paper/2412.13735/) (2024)
- [MonoSE(3)-Diffusion: A Monocular SE(3) Diffusion Framework for Robust Camera-to-Robot Pose Estimation](https://mlsanity.com/paper/2510.10434/) (2025)
- [Few-Shot Incremental 3D Object Detection in Dynamic Indoor Environments](https://mlsanity.com/paper/2604.07997/) (2026)
- [Iterative Feedback Network for Unsupervised Point Cloud Registration](https://mlsanity.com/paper/2401.04357/) (2024)
- [Accurate Ground-Truth Depth Image Generation via Overfit Training of Point Cloud Registration using Local Frame Sets](https://mlsanity.com/paper/2207.07016/) (2022)
- [One-Nearest Neighborhood Guides Inlier Estimation for Unsupervised Point Cloud Registration](https://mlsanity.com/paper/2307.14019/) (2023)
- [VioLA: Aligning Videos to 2D LiDAR Scans](https://mlsanity.com/paper/2311.04783/) (2023)
- [Unsupervised Point Cloud Registration via Training-Time Semantic Guidance](https://mlsanity.com/paper/2609.15228/) (2026)

## Abstract (arXiv)

In this paper, by modeling the point cloud registration task as a Markov decision process, we propose an end-to-end deep model embedded with the cross-entropy method (CEM) for unsupervised 3D registration. Our model consists of a sampling network module and a differentiable CEM module. In our sampling network module, given a pair of point clouds, the sampling network learns a prior sampling distribution over the transformation space. The learned sampling distribution can be used as a "good" initialization of the differentiable CEM module. In our differentiable CEM module, we first propose a maximum consensus criterion based alignment metric as the reward function for the point cloud registration task. Based on the reward function, for each state, we then construct a fused score function to evaluate the sampled transformations, where we weight the current and future rewards of the transformations. Particularly, the future rewards of the sampled transforms are obtained by performing the iterative closest point (ICP) algorithm on the transformed state. By selecting the top-k transformations with the highest scores, we iteratively update the sampling distribution. Furthermore, in order to make the CEM differentiable, we use the sparsemax function to replace the hard top-k selection. Finally, we formulate a Geman-McClure estimator based loss to train our end-to-end registration model. Extensive experimental results demonstrate the good registration performance of our method on benchmark datasets.