Self-Attention Based Multi-Scale Graph Auto-Encoder Network of 3D Meshes
This work addresses the problem of accurate 3D mesh reconstruction for computer vision and graphics applications, representing an incremental improvement over existing GCN methods.
The paper tackles the challenge of extending neural networks to irregular 3D meshes by introducing 3DGeoMeshNet, a GCN-based framework that uses anisotropic convolution layers to learn global and local features directly in the spatial domain, achieving improved reconstruction accuracy on the COMA dataset of human faces.
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.