DMesh: A Differentiable Mesh Representation
Sanghyun Son, Matheus Gadelha, Yang Zhou, Zexiang Xu, Ming Lin, Yi Zhou
Abstract
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 clouds and multi-view images using gradient-based optimization. We publicize the source code and supplementary material at our project page (https://sonsang.github.io/dmesh-project).
BibTeX
@inproceedings{
son2024dmesh,
title={{DM}esh: A Differentiable Mesh Representation},
author={Sanghyun Son and Matheus Gadelha and Yang Zhou and Zexiang Xu and Ming Lin and Yi Zhou},
booktitle={The Thirty-eighth Annual Conference on Neural Information Processing Systems},
year={2024},
url={https://openreview.net/forum?id=Io1qKqCVIK}
}