# Skeletal Point Representations with Geometric Deep Learning

arXiv: https://arxiv.org/abs/2303.02123 · HTML: https://mlsanity.com/paper/2303.02123/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 16 references that are in the map.
- First posted on arXiv 3 Mar 2023.

## Builds on (most cited first, 4 of 4)

- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [Unsupervised Learning of Intrinsic Structural Representation Points](https://mlsanity.com/paper/2003.01661/) (2020)
- [Point2Skeleton: Learning Skeletal Representations from Point Clouds](https://mlsanity.com/paper/2012.00230/) (2020)
- [DeepSkeleton: Learning Multi-task Scale-associated Deep Side Outputs for Object Skeleton Extraction in Natural Images](https://mlsanity.com/paper/1609.03659/) (2016)

## Built on by (most cited first, 1 of 1)

- [Fitting Skeletal Models via Graph-based Learning](https://mlsanity.com/paper/2409.05311/) (2024)

## Abstract (arXiv)

Skeletonization has been a popular shape analysis technique that models both the interior and exterior of an object. Existing template-based calculations of skeletal models from anatomical structures are a time-consuming manual process. Recently, learning-based methods have been used to extract skeletons from 3D shapes. In this work, we propose novel additional geometric terms for calculating skeletal structures of objects. The results are similar to traditional fitted s-reps but but are produced much more quickly. Evaluation on real clinical data shows that the learned model predicts accurate skeletal representations and shows the impact of proposed geometric losses along with using s-reps as weak supervision.