metadata
tags:
- model_hub_mixin
- pytorch_model_hub_mixin
license: apache-2.0
pipeline_tag: text-to-3d
FastMesh: Efficient Artistic Mesh Generation via Component Decoupling
This model has been pushed to the Hub using the PytorchModelHubMixin integration.
FastMesh is an efficient framework that generates artistic meshes by treating vertices and faces separately, significantly reducing redundancy and achieving more than 8x faster speed on mesh generation compared to state-of-the-art approaches, while producing higher mesh quality.
- 📚 Paper: FastMesh: Efficient Artistic Mesh Generation via Component Decoupling
- 🏠 Project Page: https://jhkim0759.github.io/projects/FastMesh/
- 💻 Code: https://github.com/jhkim0759/FastMesh
💡 Quick Start
Generate meshes from sampled point cloud with V1K variant:
python inference.py --mesh_path assets --variant V1K --batch_size 3
Generate meshes from sampled point cloud with V4K variant:
python inference.py --mesh_path assets --variant V4K --batch_size 1
📚 Citation
If you find our work helpful, please consider citing:
@misc{kim2025fastmesh,
title={FastMesh: Efficient Artistic Mesh Generation via Component Decoupling},
author={Jeonghwan Kim and Yushi Lan and Armando Fortes and Yongwei Chen and Xingang Pan},
year={2025},
eprint={2508.19188},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2508.19188},
}