Learning Local Neighboring Structure for Robust 3D Shape Representation

Authors

  • Zhongpai Gao Shanghai Jiao Tong University
  • Junchi Yan Shanghai Jiao Tong University
  • Guangtao Zhai Shanghai Jiao Tong University
  • Juyong Zhang University of Science and Technology of China
  • Yiyan Yang Shanghai Jiao Tong University
  • Xiaokang Yang Shanghai Jiao Tong University

Keywords:

3D Computer Vision

Abstract

Mesh is a powerful data structure for 3D shapes. Representation learning for 3D meshes is important in many computer vision and graphics applications. The recent success of convolutional neural networks (CNNs) for structured data (e.g., images) suggests the value of adapting insight from CNN for 3D shapes. However, 3D shape data are irregular since each node's neighbors are unordered. Various graph neural networks for 3D shapes have been developed with isotropic filters or predefined local coordinate systems to overcome the node inconsistency on graphs. However, isotropic filters or predefined local coordinate systems limit the representation power. In this paper, we propose a local structure-aware anisotropic convolutional operation (LSA-Conv) that learns adaptive weighting matrices for each node according to the local neighboring structure and performs shared anisotropic filters. In fact, the learnable weighting matrix is similar to the attention matrix in random synthesizer -- a new Transformer model for natural language processing (NLP). Comprehensive experiments demonstrate that our model produces significant improvement in 3D shape reconstruction compared to state-of-the-art methods.

Downloads

Published

2021-05-18

How to Cite

Gao, Z., Yan, J., Zhai, G., Zhang, J., Yang, Y., & Yang, X. (2021). Learning Local Neighboring Structure for Robust 3D Shape Representation. Proceedings of the AAAI Conference on Artificial Intelligence, 35(2), 1397-1405. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/16229

Issue

Section

AAAI Technical Track on Computer Vision I