# Learning general and distinctive 3D local deep descriptors for point cloud registration

arXiv: https://arxiv.org/abs/2105.10382 · HTML: https://mlsanity.com/paper/2105.10382/

## Key facts

- Cited by 42 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 35 references that are in the map.
- First posted on arXiv 21 May 2021.

## Builds on (most cited first, 18 of 18)

- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [KPConv: Flexible and Deformable Convolution for Point Clouds](https://mlsanity.com/paper/1904.08889/) (2019)
- [Open3D: A Modern Library for 3D Data Processing](https://mlsanity.com/paper/1801.09847/) (2018)
- [PPFNet: Global Context Aware Local Features for Robust 3D Point Matching](https://mlsanity.com/paper/1802.02669/) (2018)
- [D3Feat: Joint Learning of Dense Detection and Description of 3D Local Features](https://mlsanity.com/paper/2003.03164/) (2020)
- [The Perfect Match: 3D Point Cloud Matching with Smoothed Densities](https://mlsanity.com/paper/1811.06879/) (2018)
- [SpinNet: Learning a General Surface Descriptor for 3D Point Cloud Registration](https://mlsanity.com/paper/2011.12149/) (2020)
- [PPF-FoldNet: Unsupervised Learning of Rotation Invariant 3D Local Descriptors](https://mlsanity.com/paper/1808.10322/) (2018)
- [3D Point Capsule Networks](https://mlsanity.com/paper/1812.10775/) (2018)
- [3DFeat-Net: Weakly Supervised Local 3D Features for Point Cloud Registration](https://mlsanity.com/paper/1807.09413/) (2018)
- [End-to-End Learning Local Multi-view Descriptors for 3D Point Clouds](https://mlsanity.com/paper/2003.05855/) (2020)
- [Learning Compact Geometric Features](https://mlsanity.com/paper/1709.05056/) (2017)
- [Rotational Projection Statistics for 3D Local Surface Description and Object Recognition](https://mlsanity.com/paper/1304.3192/) (2013)
- [3D Local Features for Direct Pairwise Registration](https://mlsanity.com/paper/1904.04281/) (2019)
- [Distinctive 3D local deep descriptors](https://mlsanity.com/paper/2009.00258/) (2020)
- [Learning an Effective Equivariant 3D Descriptor Without Supervision](https://mlsanity.com/paper/1909.06887/) (2019)
- [Iterative Transformer Network for 3D Point Cloud](https://mlsanity.com/paper/1811.11209/) (2018)

## Built on by (most cited first, 30 of 42)

- [FreeZe: Training-free zero-shot 6D pose estimation with geometric and vision foundation models](https://mlsanity.com/paper/2312.00947/) (2023)
- [Any6D: Model-free 6D Pose Estimation of Novel Objects](https://mlsanity.com/paper/2503.18673/) (2025)
- [GIPSO: Geometrically Informed Propagation for Online Adaptation in 3D LiDAR Segmentation](https://mlsanity.com/paper/2207.09763/) (2022)
- [Open-vocabulary object 6D pose estimation](https://mlsanity.com/paper/2312.00690/) (2023)
- [KISS-Matcher: Fast and Robust Point Cloud Registration Revisited](https://mlsanity.com/paper/2409.15615/) (2024)
- [Accurate and efficient zero-shot 6D pose estimation with frozen foundation models](https://mlsanity.com/paper/2506.09784/) (2025)
- [TurboReg: TurboClique for Robust and Efficient Point Cloud Registration](https://mlsanity.com/paper/2507.01439/) (2025)
- [UNOPose: Unseen Object Pose Estimation with an Unposed RGB-D Reference Image](https://mlsanity.com/paper/2411.16106/) (2024)
- [G3Reg: Pyramid Graph-based Global Registration using Gaussian Ellipsoid Model](https://mlsanity.com/paper/2308.11573/) (2023)
- [Overlap-guided Gaussian Mixture Models for Point Cloud Registration](https://mlsanity.com/paper/2210.09836/) (2022)
- [Register Any Point: Scaling 3D Point Cloud Registration by Flow Matching](https://mlsanity.com/paper/2512.01850/) (2025)
- [COLA: COarse-LAbel multi-source LiDAR semantic segmentation for autonomous driving](https://mlsanity.com/paper/2311.03017/) (2023)
- [BUFFER-X: Towards Zero-Shot Point Cloud Registration in Diverse Scenes](https://mlsanity.com/paper/2503.07940/) (2025)
- [Revisiting Fully Convolutional Geometric Features for Object 6D Pose Estimation](https://mlsanity.com/paper/2307.15514/) (2023)
- [Data Augmentation-free Unsupervised Learning for 3D Point Cloud Understanding](https://mlsanity.com/paper/2210.02798/) (2022)
- [PointDifformer: Robust Point Cloud Registration With Neural Diffusion and Transformer](https://mlsanity.com/paper/2404.14034/) (2024)
- [Weak-to-Strong 3D Object Detection with X-Ray Distillation](https://mlsanity.com/paper/2404.00679/) (2024)
- [Unlocking Generalization Power in LiDAR Point Cloud Registration](https://mlsanity.com/paper/2503.10149/) (2025)
- [Novel class discovery meets foundation models for 3D semantic segmentation](https://mlsanity.com/paper/2312.03782/) (2023)
- [ML-SemReg: Boosting Point Cloud Registration with Multi-level Semantic Consistency](https://mlsanity.com/paper/2407.09862/) (2024)
- [PointRegGPT: Boosting 3D Point Cloud Registration using Generative Point-Cloud Pairs for Training](https://mlsanity.com/paper/2407.14054/) (2024)
- [Distilling 3D distinctive local descriptors for 6D pose estimation](https://mlsanity.com/paper/2503.15106/) (2025)
- [PatchMixer: Rethinking network design to boost generalization for 3D point cloud understanding](https://mlsanity.com/paper/2307.15692/) (2023)
- [Fully-Geometric Cross-Attention for Point Cloud Registration](https://mlsanity.com/paper/2502.08285/) (2025)
- [Automated 3D-GS Registration and Fusion via Skeleton Alignment and Gaussian-Adaptive Features](https://mlsanity.com/paper/2507.20480/) (2025)
- [3D Registration in 30 Years: A Survey](https://mlsanity.com/paper/2412.13735/) (2024)
- [CHIP: A multi-sensor dataset for 6D pose estimation of chairs in industrial settings](https://mlsanity.com/paper/2506.09699/) (2025)
- [UniMesh: Unifying 3D Mesh Understanding and Generation](https://mlsanity.com/paper/2604.17472/) (2026)
- [QuadricsReg: Large-Scale Point Cloud Registration using Quadric Primitives](https://mlsanity.com/paper/2412.02998/) (2024)
- [Correspondence-Free Fast and Robust Spherical Point Pattern Registration](https://mlsanity.com/paper/2508.02339/) (2025)

## Abstract (arXiv)

An effective 3D descriptor should be invariant to different geometric transformations, such as scale and rotation, robust to occlusions and clutter, and capable of generalising to different application domains. We present a simple yet effective method to learn general and distinctive 3D local descriptors that can be used to register point clouds that are captured in different domains. Point cloud patches are extracted, canonicalised with respect to their local reference frame, and encoded into scale and rotation-invariant compact descriptors by a deep neural network that is invariant to permutations of the input points. This design is what enables our descriptors to generalise across domains. We evaluate and compare our descriptors with alternative handcrafted and deep learning-based descriptors on several indoor and outdoor datasets that are reconstructed by using both RGBD sensors and laser scanners. Our descriptors outperform most recent descriptors by a large margin in terms of generalisation, and also become the state of the art in benchmarks where training and testing are performed in the same domain.