DMesh++: An Efficient Differentiable Mesh for Complex Shapes
Abstract
Recent probabilistic methods for 3D triangular meshes capture diverse shapes by differentiable mesh connectivity, but face high computational costs with increased shape details. We introduce a new differentiable mesh processing method that addresses this challenge and efficiently handles meshes with intricate structures. Our method reduces time complexity from O(N) to O(log N) and requires significantly less memory than previous approaches. Building on this innovation, we present a reconstruction algorithm capable of generating complex 2D and 3D shapes from point clouds or multi-view images. Visit https://sonsang.github.io/dmesh2-project for source code and supplementary material.
Cite
Text
Son et al. "DMesh++: An Efficient Differentiable Mesh for Complex Shapes." International Conference on Computer Vision, 2025.Markdown
[Son et al. "DMesh++: An Efficient Differentiable Mesh for Complex Shapes." International Conference on Computer Vision, 2025.](https://mlanthology.org/iccv/2025/son2025iccv-dmesh/)BibTeX
@inproceedings{son2025iccv-dmesh,
title = {{DMesh++: An Efficient Differentiable Mesh for Complex Shapes}},
author = {Son, Sanghyun and Gadelha, Matheus and Zhou, Yang and Fisher, Matthew and Xu, Zexiang and Qiao, Yi-Ling and Lin, Ming C. and Zhou, Yi},
booktitle = {International Conference on Computer Vision},
year = {2025},
pages = {26590-26599},
url = {https://mlanthology.org/iccv/2025/son2025iccv-dmesh/}
}