# Unsupervised Deep Probabilistic Approach for Partial Point Cloud Registration

arXiv: https://arxiv.org/abs/2303.13290 · HTML: https://mlsanity.com/paper/2303.13290/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 57 references that are in the map.
- First posted on arXiv 23 Mar 2023.

## Builds on (most cited first, 30 of 34)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances](https://mlsanity.com/paper/1306.0895/) (2013)
- [KPConv: Flexible and Deformable Convolution for Point Clouds](https://mlsanity.com/paper/1904.08889/) (2019)
- [PointContrast: Unsupervised Pre-training for 3D Point Cloud Understanding](https://mlsanity.com/paper/2007.10985/) (2020)
- [3DMatch: Learning Local Geometric Descriptors from RGB-D Reconstructions](https://mlsanity.com/paper/1603.08182/) (2016)
- [Deep Closest Point: Learning Representations for Point Cloud Registration](https://mlsanity.com/paper/1905.03304/) (2019)
- [PREDATOR: Registration of 3D Point Clouds with Low Overlap](https://mlsanity.com/paper/2011.13005/) (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)
- [Geometric Transformer for Fast and Robust Point Cloud Registration](https://mlsanity.com/paper/2202.06688/) (2022)
- [RPM-Net: Robust Point Matching using Learned Features](https://mlsanity.com/paper/2003.13479/) (2020)
- [D3Feat: Joint Learning of Dense Detection and Description of 3D Local Features](https://mlsanity.com/paper/2003.03164/) (2020)
- [CoFiNet: Reliable Coarse-to-fine Correspondences for Robust Point Cloud Registration](https://mlsanity.com/paper/2110.14076/) (2021)
- [PRNet: Self-Supervised Learning for Partial-to-Partial Registration](https://mlsanity.com/paper/1910.12240/) (2019)
- [SpinNet: Learning a General Surface Descriptor for 3D Point Cloud Registration](https://mlsanity.com/paper/2011.12149/) (2020)
- [PointDSC: Robust Point Cloud Registration using Deep Spatial Consistency](https://mlsanity.com/paper/2103.05465/) (2021)
- [PPF-FoldNet: Unsupervised Learning of Rotation Invariant 3D Local Descriptors](https://mlsanity.com/paper/1808.10322/) (2018)
- [Feature-metric Registration: A Fast Semi-supervised Approach for Robust Point Cloud Registration without Correspondences](https://mlsanity.com/paper/2005.01014/) (2020)
- [Robust Point Cloud Registration Framework Based on Deep Graph Matching](https://mlsanity.com/paper/2103.04256/) (2021)
- [3DRegNet: A Deep Neural Network for 3D Point Registration](https://mlsanity.com/paper/1904.01701/) (2019)
- [REGTR: End-to-end Point Cloud Correspondences with Transformers](https://mlsanity.com/paper/2203.14517/) (2022)
- [DeepGMR: Learning Latent Gaussian Mixture Models for Registration](https://mlsanity.com/paper/2008.09088/) (2020)
- [OMNet: Learning Overlapping Mask for Partial-to-Partial Point Cloud Registration](https://mlsanity.com/paper/2103.00937/) (2021)
- [UnsupervisedR&R: Unsupervised Point Cloud Registration via Differentiable Rendering](https://mlsanity.com/paper/2102.11870/) (2021)
- [FilterReg: Robust and Efficient Probabilistic Point-Set Registration using Gaussian Filter and Twist Parameterization](https://mlsanity.com/paper/1811.10136/) (2018)
- [PatchFormer: An Efficient Point Transformer with Patch Attention](https://mlsanity.com/paper/2111.00207/) (2021)
- [Self-supervised Geometric Perception](https://mlsanity.com/paper/2103.03114/) (2021)
- [Sampling Network Guided Cross-Entropy Method for Unsupervised Point Cloud Registration](https://mlsanity.com/paper/2109.06619/) (2021)
- [Reliable Inlier Evaluation for Unsupervised Point Cloud Registration](https://mlsanity.com/paper/2202.11292/) (2022)
- [Joint Alignment of Multiple Point Sets with Batch and Incremental Expectation-Maximization](https://mlsanity.com/paper/1609.01466/) (2016)

## Built on by (most cited first, 27 of 27)

- [Extend Your Own Correspondences: Unsupervised Distant Point Cloud Registration by Progressive Distance Extension](https://mlsanity.com/paper/2403.03532/) (2024)
- [Geometrically-driven Aggregation for Zero-shot 3D Point Cloud Understanding](https://mlsanity.com/paper/2312.02244/) (2023)
- [ZeroReg: Zero-Shot Point Cloud Registration with Foundation Models](https://mlsanity.com/paper/2312.03032/) (2023)
- [Point Tree Transformer for Point Cloud Registration](https://mlsanity.com/paper/2406.17530/) (2024)
- [EM-MIAs: Enhancing Membership Inference Attacks in Large Language Models through Ensemble Modeling](https://mlsanity.com/paper/2412.17249/) (2024)
- [RARE: Refine Any Registration of Pairwise Point Clouds via Zero-Shot Learning](https://mlsanity.com/paper/2507.19950/) (2025)
- [Quantity-Aware Coarse-to-Fine Correspondence for Image-to-Point Cloud Registration](https://mlsanity.com/paper/2307.07142/) (2023)
- [Unsupervised Point Cloud Registration with Self-Distillation](https://mlsanity.com/paper/2409.07558/) (2024)
- [Diff-Reg v1: Diffusion Matching Model for Registration Problem](https://mlsanity.com/paper/2403.19919/) (2024)
- [Fully-Geometric Cross-Attention for Point Cloud Registration](https://mlsanity.com/paper/2502.08285/) (2025)
- [DBDNet:Partial-to-Partial Point Cloud Registration with Dual Branches Decoupling](https://mlsanity.com/paper/2310.11733/) (2023)
- [Deep-PE: A Learning-Based Pose Evaluator for Point Cloud Registration](https://mlsanity.com/paper/2405.16085/) (2024)
- [3D Registration in 30 Years: A Survey](https://mlsanity.com/paper/2412.13735/) (2024)
- [Iterative Feedback Network for Unsupervised Point Cloud Registration](https://mlsanity.com/paper/2401.04357/) (2024)
- [CSCPR: Cross-Source-Context Indoor RGB-D Place Recognition](https://mlsanity.com/paper/2407.17457/) (2024)
- [Mining and Transferring Feature-Geometry Coherence for Unsupervised Point Cloud Registration](https://mlsanity.com/paper/2411.01870/) (2024)
- [Toward Zero-Shot Point Cloud Registration Across Diverse Scales, Scenes, and Sensor Setups](https://mlsanity.com/paper/2601.02759/) (2026)
- [COG: Confidence-aware Optimal Geometric Correspondence for Unsupervised Single-reference Novel Object Pose Estimation](https://mlsanity.com/paper/2603.00493/) (2026)
- [GLASS: Graph and Vision-Language Assisted Semantic Shape Correspondence](https://mlsanity.com/paper/2603.07652/) (2026)
- [One-Nearest Neighborhood Guides Inlier Estimation for Unsupervised Point Cloud Registration](https://mlsanity.com/paper/2307.14019/) (2023)
- [UniRiT: Towards Few-Shot Non-Rigid Point Cloud Registration](https://mlsanity.com/paper/2410.22909/) (2024)
- [PKSS-Align: Robust Point Cloud Registration on Pre-Kendall Shape Space](https://mlsanity.com/paper/2508.04286/) (2025)
- [Leveraging Cycle-Consistent Anchor Points for Self-Supervised RGB-D Registration](https://mlsanity.com/paper/2510.14354/) (2025)
- [Clustering-Enhanced Domain Adaptation for Cross-Domain Intrusion Detection in Industrial Control Systems](https://mlsanity.com/paper/2604.12183/) (2026)
- [C-GenReg: Training-Free 3D Point Cloud Registration by Multi-View-Consistent Geometry-to-Image Generation with Probabilistic Modalities Fusion](https://mlsanity.com/paper/2604.16680/) (2026)
- [Medoid Prototype Alignment for Cross-Plant Unknown Attack Detection in Industrial Control Systems](https://mlsanity.com/paper/2604.25544/) (2026)
- [Unsupervised Point Cloud Registration via Training-Time Semantic Guidance](https://mlsanity.com/paper/2609.15228/) (2026)

## Abstract (arXiv)

Deep point cloud registration methods face challenges to partial overlaps and rely on labeled data. To address these issues, we propose UDPReg, an unsupervised deep probabilistic registration framework for point clouds with partial overlaps. Specifically, we first adopt a network to learn posterior probability distributions of Gaussian mixture models (GMMs) from point clouds. To handle partial point cloud registration, we apply the Sinkhorn algorithm to predict the distribution-level correspondences under the constraint of the mixing weights of GMMs. To enable unsupervised learning, we design three distribution consistency-based losses: self-consistency, cross-consistency, and local contrastive. The self-consistency loss is formulated by encouraging GMMs in Euclidean and feature spaces to share identical posterior distributions. The cross-consistency loss derives from the fact that the points of two partially overlapping point clouds belonging to the same clusters share the cluster centroids. The cross-consistency loss allows the network to flexibly learn a transformation-invariant posterior distribution of two aligned point clouds. The local contrastive loss facilitates the network to extract discriminative local features. Our UDPReg achieves competitive performance on the 3DMatch/3DLoMatch and ModelNet/ModelLoNet benchmarks.