Mesh Classification With Dilated Mesh Convolutions

Abstract

Unlike images, meshes are irregular and unstructured. Thus, it is not trivial to extend existing image-based deep learning approaches for mesh analysis. In this paper, inspired by dilated convolutions for images, we proffer dilated convolutions for meshes. Our Dilated Mesh Convolution (DMC) unit inflates the kernels' receptive field without increasing the number of learnable parameters. We also propose a Stacked Dilated Mesh Convolution (SDMC) block by stacking DMC units. It considers spatial regions around mesh faces' at multiple scales while summarizing the neighboring contextual information. We accommodated SDMC in MeshNet to classify 3D meshes. Experimental results demonstrate that this redesigned model significantly improves classification accuracy on multiple data sets. Code

A Survey on Graph Neural Networks and Graph Transformers in Computer Vision: A Task-Oriented Perspective

“…The polygonal mesh discretely represents the surface of a 3D shape with faces and vertices. Since it can be viewed as an undirected graph, mainstream GNNs or graph Transformers can be used for 3D mesh analysis [247], [248], [249], [250], [251], [252], [253], [254], [255], [256], [257], [258], [259].…”

“…Besides, SpiralNet++ [251] presents a fast and efficient intrinsic mesh convolution operator that improves [261] by fusing neighboring node features with local geometric structure information at multiple scales. A stacked dilated mesh convolution block is proposed in [253] that can inflate the receptive field of graph convolution kernels. PolyNet [254] designs a specific polygon mesh representation with a multi-resolution structure, and two operations, polynomial convolution and pooling, invariant to the number of adjacent vertices, their permutations, and their pairwise distances in local patches.…”