MeshNet: Mesh Neural Network for 3D Shape Representation

By Yutong Feng, Yifan Feng, Haoxuan You, Xibin Zhao, Yue Gao. AAAI Conference on Artificial Intelligence, 2018

367 citations recorded by the source corpus.

Mesh is an important and powerful type of data for 3D shapes and widely studied in the field of computer vision and computer graphics. Regarding the task of 3D shape representation, there have been extensive research efforts concentrating on how to represent 3D shapes well using volumetric grid, multi-view and point cloud. However, there is little effort on using mesh data in recent years, due to the complexity and irregularity of mesh data. In this paper, we propose a mesh neural network, named MeshNet, to learn 3D shape representation from mesh data. In this method, face-unit and feature splitting are introduced, and a general architecture with available and effective blocks are proposed. In this way, MeshNet is able to solve the complexity and irregularity problem of mesh and conduct 3D shape representation well. We have applied the proposed MeshNet method in the applications of 3D shape classification and retrieval. Experimental results and comparisons with the state-of-the-art methods demonstrate that the proposed MeshNet can achieve satisfying 3D shape classification and retrieval performance, which indicates the effectiveness of the proposed method on 3D shape representation.

Subfields: Computational Mechanics, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/35bb00d21bfc8e13959b7ddb863e6254f778bebe

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Mechanics

1. Keenan Crane
2. Souhaib Attaiki
3. Nicholas Sharp
4. Huan Fu
5. Dacheng Tao
6. S. Maybank
7. Lin Gao
8. M. Ovsjanikov

In Computer Vision and Pattern Recognition

1. Dacheng Tao
2. Huan Fu
3. S. Maybank
4. Mingming Gong
5. Keenan Crane
6. Souhaib Attaiki
7. Nicholas Sharp
8. Lin Gao

Citations in the corpus

• DiffusionNet: Discretization Agnostic Learning on Surfaces (2020, methodology): “Surface mesh structure has also been exploited in variety of graph-like approaches which specifically leverage mesh connectivity [Bodnar et al. 2021; Feng et al. 2019; Gong et al. 2019; Hajij et al. 2020; Hanocka et al. 2019; Lim et al. 2018; Milano et al. 2020; Verma et al. 2018], the structure of ”
• A Survey on Vision--Language--Action Models for Embodied AI (2024, neutral): “Despite the widespread use of 3D meshes as the default data format in computer graphics, their irregular nature poses challenges for neural networks [258].”
• 3D-FUTURE: 3D Furniture Shape with TextURE (2020, background): “…(Ji et al., 2012), some researchers prefer to either develop special deep learning operations on point clouds and mesh surfaces (Qi et al., 2017a,b; Hanocka et al., 2019; Feng et al., 2019), or project 3D shapes to several 2D images and then apply 2D convolutional networks (Su et al., 2015).”