Dual Mesh Convolutional Networks for Human Shape Correspondence

TL;DR

This paper introduces a dual mesh convolutional network approach for human shape correspondence, leveraging face-based mesh representations to improve robustness and accuracy over traditional primal mesh methods.

Contribution

It proposes using dual face-based mesh representations in graph convolutional networks, enhancing robustness and performance in shape correspondence tasks.

Findings

Dual mesh approach improves shape correspondence accuracy.

Models leveraging dual mesh neighborhoods are more robust to topology changes.

Dual mesh networks outperform primal mesh networks in experiments.

Abstract

Convolutional networks have been extremely successful for regular data structures such as 2D images and 3D voxel grids. The transposition to meshes is, however, not straight-forward due to their irregular structure. We explore how the dual, face-based representation of triangular meshes can be leveraged as a data structure for graph convolutional networks. In the dual mesh, each node (face) has a fixed number of neighbors, which makes the networks less susceptible to overfitting on the mesh topology, and also al-lows the use of input features that are naturally defined over faces, such as surface normals and face areas. We evaluate the dual approach on the shape correspondence task on theFaust human shape dataset and variants of it with differ-ent mesh topologies. Our experiments show that results of graph convolutional networks improve when defined over the dual rather than primal mesh. Moreover, our models that explicitly leverage the neighborhood regularity of dual meshes allow improving results further while being more robust to changes in the mesh topology.