# Neural ShDF: Reviving an Efficient and Consistent Mesh Segmentation Method

arXiv: https://arxiv.org/abs/2306.11737 · HTML: https://mlsanity.com/paper/2306.11737/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 46 references that are in the map.
- First posted on arXiv 14 Jun 2023.

## Builds on (most cited first, 6 of 6)

- [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)
- [3D Semantic Segmentation with Submanifold Sparse Convolutional Networks](https://mlsanity.com/paper/1711.10275/) (2017)
- [MeshCNN: A Network with an Edge](https://mlsanity.com/paper/1809.05910/) (2018)
- [Deep Learning for Medical Image Segmentation](https://mlsanity.com/paper/1505.02000/) (2015)
- [GraphSeam: Supervised Graph Learning Framework for Semantic UV Mapping](https://mlsanity.com/paper/2011.13748/) (2020)

## Built on by (most cited first, 2 of 2)

- [Segment Any Mesh](https://mlsanity.com/paper/2408.13679/) (2024)
- [GeoSAM2: Unleashing the Power of SAM2 for 3D Part Segmentation](https://mlsanity.com/paper/2508.14036/) (2025)

## Abstract (arXiv)

Partitioning a polygonal mesh into meaningful parts can be challenging. Many applications require decomposing such structures for further processing in computer graphics. In the last decade, several methods were proposed to tackle this problem, at the cost of intensive computational times. Recently, machine learning has proven to be effective for the segmentation task on 3D structures. Nevertheless, these state-of-the-art methods are often hardly generalizable and require dividing the learned model into several specific classes of objects to avoid overfitting. We present a data-driven approach leveraging deep learning to encode a mapping function prior to mesh segmentation for multiple applications. Our network reproduces a neighborhood map using our knowledge of the textslShape Diameter Function (SDF) method using similarities among vertex neighborhoods. Our approach is resolution-agnostic as we downsample the input meshes and query the full-resolution structure solely for neighborhood contributions. Using our predicted SDF values, we can inject the resulting structure into a graph-cut algorithm to generate an efficient and robust mesh segmentation while considerably reducing the required computation times.