Enregistré dans:
Détails bibliographiques
Auteurs principaux: Lyu, Zhaoyang, Fei, Ben, Wang, Jinyi, Xu, Xudong, Zhang, Ya, Yang, Weidong, Dai, Bo
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:https://arxiv.org/abs/2403.11990
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866916164107501568
author Lyu, Zhaoyang
Fei, Ben
Wang, Jinyi
Xu, Xudong
Zhang, Ya
Yang, Weidong
Dai, Bo
author_facet Lyu, Zhaoyang
Fei, Ben
Wang, Jinyi
Xu, Xudong
Zhang, Ya
Yang, Weidong
Dai, Bo
contents Mesh is a fundamental representation of 3D assets in various industrial applications, and is widely supported by professional softwares. However, due to its irregular structure, mesh creation and manipulation is often time-consuming and labor-intensive. In this paper, we propose a highly controllable generative model, GetMesh, for mesh generation and manipulation across different categories. By taking a varying number of points as the latent representation, and re-organizing them as triplane representation, GetMesh generates meshes with rich and sharp details, outperforming both single-category and multi-category counterparts. Moreover, it also enables fine-grained control over the generation process that previous mesh generative models cannot achieve, where changing global/local mesh topologies, adding/removing mesh parts, and combining mesh parts across categories can be intuitively, efficiently, and robustly accomplished by adjusting the number, positions or features of latent points. Project page is https://getmesh.github.io.
format Preprint
id arxiv_https___arxiv_org_abs_2403_11990
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle GetMesh: A Controllable Model for High-quality Mesh Generation and Manipulation
Lyu, Zhaoyang
Fei, Ben
Wang, Jinyi
Xu, Xudong
Zhang, Ya
Yang, Weidong
Dai, Bo
Computer Vision and Pattern Recognition
Mesh is a fundamental representation of 3D assets in various industrial applications, and is widely supported by professional softwares. However, due to its irregular structure, mesh creation and manipulation is often time-consuming and labor-intensive. In this paper, we propose a highly controllable generative model, GetMesh, for mesh generation and manipulation across different categories. By taking a varying number of points as the latent representation, and re-organizing them as triplane representation, GetMesh generates meshes with rich and sharp details, outperforming both single-category and multi-category counterparts. Moreover, it also enables fine-grained control over the generation process that previous mesh generative models cannot achieve, where changing global/local mesh topologies, adding/removing mesh parts, and combining mesh parts across categories can be intuitively, efficiently, and robustly accomplished by adjusting the number, positions or features of latent points. Project page is https://getmesh.github.io.
title GetMesh: A Controllable Model for High-quality Mesh Generation and Manipulation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2403.11990