DMesh++: An Efficient Differentiable Mesh for Complex Shapes

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Son, Sanghyun, Gadelha, Matheus, Zhou, Yang, Fisher, Matthew, Xu, Zexiang, Qiao, Yi-Ling, Lin, Ming C., Zhou, Yi
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915372794380288
author Son, Sanghyun
Gadelha, Matheus
Zhou, Yang
Fisher, Matthew
Xu, Zexiang
Qiao, Yi-Ling
Lin, Ming C.
Zhou, Yi
author_facet Son, Sanghyun
Gadelha, Matheus
Zhou, Yang
Fisher, Matthew
Xu, Zexiang
Qiao, Yi-Ling
Lin, Ming C.
Zhou, Yi
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2412_16776
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle DMesh++: An Efficient Differentiable Mesh for Complex Shapes
Son, Sanghyun
Gadelha, Matheus
Zhou, Yang
Fisher, Matthew
Xu, Zexiang
Qiao, Yi-Ling
Lin, Ming C.
Zhou, Yi
Computer Vision and Pattern Recognition
Graphics
Machine Learning
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.
title DMesh++: An Efficient Differentiable Mesh for Complex Shapes
topic Computer Vision and Pattern Recognition
Graphics
Machine Learning
url https://arxiv.org/abs/2412.16776