---
title: "MAT-Net: Medial Axis Transform Network for 3D Object Recognition"
authors:
  - "Jianwei Hu"
  - "Bin Wang"
  - "Lihui Qian"
  - "Yiling Pan"
  - "Xiaohu Guo"
  - "Lingjie Liu"
  - "Wenping Wang"
doi: "10.24963/ijcai.2019/109"
url: "https://ijcai.org/proceedings/2019/109"
pdf: "https://ijcai.org/proceedings/2019/0109.pdf"
venue: "Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence"
year: 2019
pages: "774-781"
track: "Main track"
keywords:
  - "Computer Vision: Computer Vision"
  - "Computer Vision: 2D and 3D Computer Vision"
  - "Computer Vision: Recognition: Detection, Categorization, Indexing, Matching, Retrieval, Semantic Interpretation"
---

# MAT-Net: Medial Axis Transform Network for 3D Object Recognition

Jianwei Hu, Bin Wang, Lihui Qian, Yiling Pan, Xiaohu Guo, Lingjie Liu, Wenping Wang

*Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence*, pages 774-781. DOI: [10.24963/ijcai.2019/109](https://doi.org/10.24963/ijcai.2019/109)

## Abstract

3D deep learning performance depends on object representation and local feature extraction. In this work, we present MAT-Net, a neural network which captures local and global features from the Medial Axis Transform (MAT). Different from K-Nearest-Neighbor method which extracts local features by a fixed number of neighbors, our MAT-Net exploits effective modules Group-MAT and Edge-Net to process topological structure. Experimental results illustrate that MAT-Net demonstrates competitive or better performance on 3D shape recognition than state-of-the-art methods, and prove that MAT representation has excellent capacity in 3D deep learning, even in the case of low resolution.