# Point2Skeleton: Learning Skeletal Representations from Point Clouds

arXiv: https://arxiv.org/abs/2012.00230 · HTML: https://mlsanity.com/paper/2012.00230/

## Key facts

- Cited by 37 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Dec 2020.

## Built on by (most cited first, 30 of 37)

- [Walk in the Cloud: Learning Curves for Point Clouds Shape Analysis](https://mlsanity.com/paper/2105.01288/) (2021)
- [Part123: Part-aware 3D Reconstruction from a Single-view Image](https://mlsanity.com/paper/2405.16888/) (2024)
- [Neural Marching Cubes](https://mlsanity.com/paper/2106.11272/) (2021)
- [MagicArticulate: Make Your 3D Models Articulation-Ready](https://mlsanity.com/paper/2502.12135/) (2025)
- [Puppeteer: Rig and Animate Your 3D Models](https://mlsanity.com/paper/2508.10898/) (2025)
- [LAKe-Net: Topology-Aware Point Cloud Completion by Localizing Aligned Keypoints](https://mlsanity.com/paper/2203.16771/) (2022)
- [CherryPicker: Semantic Skeletonization and Topological Reconstruction of Cherry Trees](https://mlsanity.com/paper/2304.04708/) (2023)
- [ScanERU: Interactive 3D Visual Grounding based on Embodied Reference Understanding](https://mlsanity.com/paper/2303.13186/) (2023)
- [Coverage Axis++: Efficient Inner Point Selection for 3D Shape Skeletonization](https://mlsanity.com/paper/2401.12946/) (2024)
- [SPEAL: Skeletal Prior Embedded Attention Learning for Cross-Source Point Cloud Registration](https://mlsanity.com/paper/2312.08664/) (2023)
- [Ges3ViG: Incorporating Pointing Gestures into Language-Based 3D Visual Grounding for Embodied Reference Understanding](https://mlsanity.com/paper/2504.09623/) (2025)
- [PDT: Point Distribution Transformation with Diffusion Models](https://mlsanity.com/paper/2507.18939/) (2025)
- [SoftGPT: Learn Goal-oriented Soft Object Manipulation Skills by Generative Pre-trained Heterogeneous Graph Transformer](https://mlsanity.com/paper/2306.12677/) (2023)
- [Inferring Neural Signed Distance Functions by Overfitting on Single Noisy Point Clouds through Finetuning Data-Driven based Priors](https://mlsanity.com/paper/2410.19680/) (2024)
- [PointNeuron: 3D Neuron Reconstruction via Geometry and Topology Learning of Point Clouds](https://mlsanity.com/paper/2210.08305/) (2022)
- [SMART-PC: Skeletal Model Adaptation for Robust Test-Time Training in Point Clouds](https://mlsanity.com/paper/2505.19546/) (2025)
- [Neural Marionette: Unsupervised Learning of Motion Skeleton and Latent Dynamics from Volumetric Video](https://mlsanity.com/paper/2202.08418/) (2022)
- [EPCS: Endpoint-based Part-aware Curve Skeleton Extraction for Low-quality Point Clouds](https://mlsanity.com/paper/2211.09488/) (2022)
- [The Sum of Its Parts: Visual Part Segmentation for Inertial Parameter Identification of Manipulated Objects](https://mlsanity.com/paper/2302.06685/) (2023)
- [Semantic keypoint extraction for scanned animals using multi-depth-camera systems](https://mlsanity.com/paper/2211.08634/) (2022)
- [Skeletal Point Representations with Geometric Deep Learning](https://mlsanity.com/paper/2303.02123/) (2023)
- [A Geometric Algorithm for Blood Vessel Reconstruction from Skeletal Representation](https://mlsanity.com/paper/2402.12797/) (2024)
- [Transferable and Undefendable Point Cloud Attacks via Medial Axis Transform](https://mlsanity.com/paper/2507.18870/) (2025)
- [High-Fidelity Medical Shape Generation via Skeletal Latent Diffusion](https://mlsanity.com/paper/2603.07504/) (2026)
- [Learning to Censor by Noisy Sampling](https://mlsanity.com/paper/2203.12192/) (2022)
- [3D Neuron Morphology Analysis](https://mlsanity.com/paper/2212.07044/) (2022)
- [Deep Medial Voxels: Learned Medial Axis Approximations for Anatomical Shape Modeling](https://mlsanity.com/paper/2403.11790/) (2024)
- [Fitting Skeletal Models via Graph-based Learning](https://mlsanity.com/paper/2409.05311/) (2024)
- [MorphoSkel3D: Morphological Skeletonization of 3D Point Clouds for Informed Sampling in Object Classification and Retrieval](https://mlsanity.com/paper/2501.12974/) (2025)
- [Skeletonization Quality Evaluation: Geometric Metrics for Point Cloud Analysis in Robotics](https://mlsanity.com/paper/2504.00032/) (2025)

## Abstract (arXiv)

We introduce Point2Skeleton, an unsupervised method to learn skeletal representations from point clouds. Existing skeletonization methods are limited to tubular shapes and the stringent requirement of watertight input, while our method aims to produce more generalized skeletal representations for complex structures and handle point clouds. Our key idea is to use the insights of the medial axis transform (MAT) to capture the intrinsic geometric and topological natures of the original input points. We first predict a set of skeletal points by learning a geometric transformation, and then analyze the connectivity of the skeletal points to form skeletal mesh structures. Extensive evaluations and comparisons show our method has superior performance and robustness. The learned skeletal representation will benefit several unsupervised tasks for point clouds, such as surface reconstruction and segmentation.