README.md

metadata

title: MeshFlow Demo
emoji: 🎨
colorFrom: indigo
colorTo: blue
sdk: gradio
sdk_version: 6.6.0
app_file: gradio_app.py
python_version: '3.10'
hardware: zero-gpu
pinned: false
license: other
license_name: fair-noncommercial-research-license
license_link: LICENSE
short_description: Generate artist-like meshes from point clouds with MeshFlow
models:
  - facebook/meshflow

MeshFlow Demo

Interactive demo for MeshFlow, an efficient artistic mesh generation model from Meta AI and HKUST (CVPR 2026 Highlight).

Upload a point cloud or mesh, optionally add a reference image, and the model returns a new artist-like mesh in about one second — preview it in the browser and download as GLB.

• Project page: https://mesh-flow.github.io/
• Source code: https://github.com/facebookresearch/meshflow
• Model card: https://huggingface.co/facebook/meshflow

Citation

@inproceedings{li2026meshflow,
  title={MeshFlow: Efficient Artistic Mesh Generation via MeshVAE and Flow-based Diffusion Transformer},
  author={Li, Weiyu and Toisoul, Antoine and Monnier, Tom and Shapovalov, Roman and Ranjan, Rakesh and Tan, Ping and Vedaldi, Andrea},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2026},
  note={Highlight}
}

License

This demo is released under the FAIR Noncommercial Research License v1. See LICENSE.