DMesh++: An Efficient Differentiable Mesh for Complex Shapes

Sanghyun Son, Matheus Gadelha, Yang Zhou, Matthew Fisher, Zexiang Xu +3 more
12/21/2024
cs.CVcs.GRcs.LG

No official code found. Best implementation: SonSang/dmesh2 (100 stars, MIT, last commit 2025-04-21). 1 more below.

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 our project page (https://sonsang.github.io/dmesh2-project) for source code and supplementary material.

View on arXivView PDF

Code Implementations(2)

SonSang/dmesh2_rendererCommunity67%
MIT

Differentiable renderer for paper "DMesh++: An Efficient Differentiable Mesh for Complex Shapes".

11C, C++Feb 24, 20251 years agoMIT
SonSang/dmesh2Community62%
MIT

Official implementation for "DMesh++: An Efficient Differentiable Mesh for Complex Shapes".

1006C, C++Dec 25, 20241 years agoMIT

Similar Papers

DMesh: A Differentiable Mesh Representation

86% match2026

PyTorchGeoNodes: Enabling Differentiable Shape Programs for 3D Shape Reconstruction

79% match2024

A Review of Deep Learning-Powered Mesh Reconstruction Methods

78% match2023

GenUDC: High Quality 3D Mesh Generation with Unsigned Dual Contouring Representation

78% match1 repo92024

MeshLRM: Large Reconstruction Model for High-Quality Meshes

78% match2024

MeshGPT: Generating Triangle Meshes with Decoder-Only Transformers

77% match2 repos6272026

Cite this paper

@article{son2024dmesh,
  title  = {DMesh++: An Efficient Differentiable Mesh for Complex Shapes},
  author = {Sanghyun Son and Matheus Gadelha and Yang Zhou and Matthew Fisher and Zexiang Xu and Yi-Ling Qiao and Ming C. Lin and Yi Zhou},
  year   = {2024},
  eprint = {2412.16776},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2412.16776v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2412.16776.svg)](https://codeofpaper.com/paper/2412.16776)

Discussion