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

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

doi:10.24963/ijcai.2019/109

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

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

Download BibTeX Cite

Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence. Main track. Pages 774-781.

https://doi.org/10.24963/ijcai.2019/109

Keywords

Computer Vision: Computer Vision
Computer Vision: 2D and 3D Computer Vision
Computer Vision: Recognition: Detection, Categorization, Indexing, Matching, Retrieval, Semantic Interpretation

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.

Jianwei Hu, Bin Wang, Lihui Qian, Yiling Pan, Xiaohu Guo, Lingjie Liu, and Wenping Wang. 2019. MAT-Net: Medial Axis Transform Network for 3D Object Recognition. In Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, IJCAI-19. IJCAI, 774–781. https://doi.org/10.24963/ijcai.2019/109

@inproceedings{ijcai2019p109,
  title     = {MAT-Net: Medial Axis Transform Network for 3D Object Recognition},
  author    = {Hu, Jianwei and Wang, Bin and Qian, Lihui and Pan, Yiling and Guo, Xiaohu and Liu, Lingjie and Wang, Wenping},
  booktitle = {Proceedings of the Twenty-Eighth International Joint Conference on
               Artificial Intelligence, {IJCAI-19}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {Sarit Kraus},
  pages     = {774--781},
  year      = {2019},
  month     = {8},
  note      = {Main track},
  doi       = {10.24963/ijcai.2019/109},
  url       = {https://doi.org/10.24963/ijcai.2019/109},
}

TY  - CPAPER
TI  - MAT-Net: Medial Axis Transform Network for 3D Object Recognition
AU  - Hu, Jianwei
AU  - Wang, Bin
AU  - Qian, Lihui
AU  - Pan, Yiling
AU  - Guo, Xiaohu
AU  - Liu, Lingjie
AU  - Wang, Wenping
T2  - Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, IJCAI-19
PB  - International Joint Conferences on Artificial Intelligence Organization
PY  - 2019
SP  - 774
EP  - 781
DO  - 10.24963/ijcai.2019/109
UR  - https://doi.org/10.24963/ijcai.2019/109
ER  -