DMesh: A Differentiable Mesh Representation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918083896016896 |
|---|---|
| author | Son, Sanghyun Gadelha, Matheus Zhou, Yang Xu, Zexiang Lin, Ming C. Zhou, Yi |
| author_facet | Son, Sanghyun Gadelha, Matheus Zhou, Yang Xu, Zexiang Lin, Ming C. Zhou, Yi |
| contents | We present a differentiable representation, DMesh, for general 3D triangular meshes. DMesh considers both the geometry and connectivity information of a mesh. In our design, we first get a set of convex tetrahedra that compactly tessellates the domain based on Weighted Delaunay Triangulation (WDT), and select triangular faces on the tetrahedra to define the final mesh. We formulate probability of faces to exist on the actual surface in a differentiable manner based on the WDT. This enables DMesh to represent meshes of various topology in a differentiable way, and allows us to reconstruct the mesh under various observations, such as point cloud and multi-view images using gradient-based optimization. The source code and full paper is available at: https://sonsang.github.io/dmesh-project. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_13445 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | DMesh: A Differentiable Mesh Representation Son, Sanghyun Gadelha, Matheus Zhou, Yang Xu, Zexiang Lin, Ming C. Zhou, Yi Computer Vision and Pattern Recognition Graphics We present a differentiable representation, DMesh, for general 3D triangular meshes. DMesh considers both the geometry and connectivity information of a mesh. In our design, we first get a set of convex tetrahedra that compactly tessellates the domain based on Weighted Delaunay Triangulation (WDT), and select triangular faces on the tetrahedra to define the final mesh. We formulate probability of faces to exist on the actual surface in a differentiable manner based on the WDT. This enables DMesh to represent meshes of various topology in a differentiable way, and allows us to reconstruct the mesh under various observations, such as point cloud and multi-view images using gradient-based optimization. The source code and full paper is available at: https://sonsang.github.io/dmesh-project. |
| title | DMesh: A Differentiable Mesh Representation |
| topic | Computer Vision and Pattern Recognition Graphics |
| url | https://arxiv.org/abs/2404.13445 |