Skip to Main content Skip to Navigation
Conference papers

Dual Mesh Convolutional Networks for Human Shape Correspondence

Nitika Verma 1 Adnane Boukhayma 2 Edmond Boyer 1 Jakob Verbeek 3
1 MORPHEO - Capture and Analysis of Shapes in Motion
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, Grenoble INP - Institut polytechnique de Grenoble - Grenoble Institute of Technology
2 MIMETIC - Analysis-Synthesis Approach for Virtual Human Simulation
UR2 - Université de Rennes 2, Inria Rennes – Bretagne Atlantique , IRISA-D6 - MEDIA ET INTERACTIONS
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 straightforward 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 allows 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 the Faust human shape dataset and variants of it with different 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.
Complete list of metadata
Contributor : Thoth Team Connect in order to contact the contributor
Submitted on : Friday, November 26, 2021 - 10:02:30 AM
Last modification on : Friday, January 21, 2022 - 3:11:15 AM


Files produced by the author(s)


  • HAL Id : hal-03450573, version 1


Nitika Verma, Adnane Boukhayma, Edmond Boyer, Jakob Verbeek. Dual Mesh Convolutional Networks for Human Shape Correspondence. 3DV 2021 - International Conference on 3D Vision, Dec 2021, Surrey, United Kingdom. pp.1-10. ⟨hal-03450573⟩



Les métriques sont temporairement indisponibles