Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2402.04821 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914684697837568 |
|---|---|
| author | Trang, Thuan Ngo, Nhat Khang Levy, Daniel Vo, Thieu N. Ravanbakhsh, Siamak Hy, Truong Son |
| author_facet | Trang, Thuan Ngo, Nhat Khang Levy, Daniel Vo, Thieu N. Ravanbakhsh, Siamak Hy, Truong Son |
| contents | Triangular meshes are widely used to represent three-dimensional objects. As a result, many recent works have address the need for geometric deep learning on 3D mesh. However, we observe that the complexities in many of these architectures does not translate to practical performance, and simple deep models for geometric graphs are competitive in practice. Motivated by this observation, we minimally extend the update equations of E(n)-Equivariant Graph Neural Networks (EGNNs) (Satorras et al., 2021) to incorporate mesh face information, and further improve it to account for long-range interactions through hierarchy. The resulting architecture, Equivariant Mesh Neural Network (EMNN), outperforms other, more complicated equivariant methods on mesh tasks, with a fast run-time and no expensive pre-processing. Our implementation is available at https://github.com/HySonLab/EquiMesh |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_04821 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | E(3)-Equivariant Mesh Neural Networks Trang, Thuan Ngo, Nhat Khang Levy, Daniel Vo, Thieu N. Ravanbakhsh, Siamak Hy, Truong Son Machine Learning Triangular meshes are widely used to represent three-dimensional objects. As a result, many recent works have address the need for geometric deep learning on 3D mesh. However, we observe that the complexities in many of these architectures does not translate to practical performance, and simple deep models for geometric graphs are competitive in practice. Motivated by this observation, we minimally extend the update equations of E(n)-Equivariant Graph Neural Networks (EGNNs) (Satorras et al., 2021) to incorporate mesh face information, and further improve it to account for long-range interactions through hierarchy. The resulting architecture, Equivariant Mesh Neural Network (EMNN), outperforms other, more complicated equivariant methods on mesh tasks, with a fast run-time and no expensive pre-processing. Our implementation is available at https://github.com/HySonLab/EquiMesh |
| title | E(3)-Equivariant Mesh Neural Networks |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2402.04821 |