MeshConv3D: Efficient convolution and pooling operators for triangular 3D meshes
This addresses the problem of efficiently processing irregular 3D meshes for tasks like semantic classification, offering a domain-specific solution with incremental improvements.
The paper tackles the challenge of extending CNNs to 3D meshes by introducing MeshConv3D, a method with specialized convolution and pooling operators that operates directly on meshes without prior conversion, achieving equivalent or superior classification results on three benchmark datasets while reducing memory and computational load.
Convolutional neural networks (CNNs) have been pivotal in various 2D image analysis tasks, including computer vision, image indexing and retrieval or semantic classification. Extending CNNs to 3D data such as point clouds and 3D meshes raises significant challenges since the very basic convolution and pooling operators need to be completely re-visited and re-defined in an appropriate manner to tackle irregular connectivity issues. In this paper, we introduce MeshConv3D, a 3D mesh-dedicated methodology integrating specialized convolution and face collapse-based pooling operators. MeshConv3D operates directly on meshes of arbitrary topology, without any need of prior re-meshing/conversion techniques. In order to validate our approach, we have considered a semantic classification task. The experimental results obtained on three distinct benchmark datasets show that the proposed approach makes it possible to achieve equivalent or superior classification results, while minimizing the related memory footprint and computational load.