Self-Attention Based Multi-Scale Graph Auto-Encoder Network of 3D Meshes

TL;DR

This paper introduces 3DGeoMeshNet, a novel graph neural network that uses anisotropic convolutions and a multi-scale encoder-decoder architecture to improve 3D mesh shape reconstruction while preserving original mesh structures.

Contribution

It proposes a new GCN-based framework with anisotropic convolutions and multi-scale processing that directly operates on meshes, outperforming previous methods in shape reconstruction accuracy.

Findings

Effective global and local feature learning in meshes

Preserves original mesh format for accurate reconstruction

Outperforms existing methods on the COMA dataset

Abstract

3D meshes are fundamental data representations for capturing complex geometric shapes in computer vision and graphics applications. While Convolutional Neural Networks (CNNs) have excelled in structured data like images, extending them to irregular 3D meshes is challenging due to the non-Euclidean nature of the data. Graph Convolutional Networks (GCNs) offer a solution by applying convolutions to graph-structured data, but many existing methods rely on isotropic filters or spectral decomposition, limiting their ability to capture both local and global mesh features. In this paper, we introduce 3D Geometric Mesh Network (3DGeoMeshNet), a novel GCN-based framework that uses anisotropic convolution layers to effectively learn both global and local features directly in the spatial domain. Unlike previous approaches that convert meshes into intermediate representations like voxel grids or point clouds, our method preserves the original polygonal mesh format throughout the reconstruction process, enabling more accurate shape reconstruction. Our architecture features a multi-scale encoder-decoder structure, where separate global and local pathways capture both large-scale geometric structures and fine-grained local details. Extensive experiments on the COMA dataset containing human faces demonstrate the efficiency of 3DGeoMeshNet in terms of reconstruction accuracy.