---
title: ActionMesh
canonical_url: "https://www.modelscope.cn/models/facebook/ActionMesh"
md_url: "https://www.modelscope.cn/models/facebook/ActionMesh.md"
repository: facebook/ActionMesh
last_updated: 2026-01-24
license: other
pipeline_tag: image-to-3D
tasks:
  - image-to-3D
model_type:
  - custom
parameters: 1.7B
tensor_type:
  - F32
library_name:
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
downloads: 108
stars: 1
tags:
  - video-to-4D
---

# ActionMesh

> ActionMesh - facebook 在 ModelScope 开源的模型。ActionMesh: Animated 3D Mesh Generation with Temporal 3D Diffusion

facebook/ActionMesh 是 ModelScope 魔搭社区上的 1.7B 参数image-to-3D模型，采用 other 许可。

- **Repository**: facebook/ActionMesh
- **License**: other
- **Tasks**: image-to-3D
- **Parameters**: 1.7B
- **Tags**: video-to-4D
- **Downloads**: 108
- **Stars**: 1
- **Last updated**: 2026-01-24

Source: https://www.modelscope.cn/models/facebook/ActionMesh

---

# ActionMesh: Animated 3D Mesh Generation with Temporal 3D Diffusion

[**ActionMesh**](https://remysabathier.github.io/actionmesh/) is a generative model that predicts production-ready 3D meshes "in action" in a feed-forward manner. It adapts 3D diffusion to include a temporal axis, allowing the generation of synchronized latents representing time-varying 3D shapes.

[[Paper](https://huggingface.co/papers/2601.16148)] [[Project Page](https://remysabathier.github.io/actionmesh/)] [[GitHub](https://github.com/facebookresearch/actionmesh)] [[Demo](https://huggingface.co/spaces/facebook/ActionMesh)]

## Installation

ActionMesh requires an NVIDIA GPU with at least 32GB VRAM.

```bash
git clone https://github.com/facebookresearch/actionmesh.git
cd actionmesh
git submodule update --init --recursive
pip install -r requirements.txt
pip install -e .
```

## Quick Start

You can generate an animated mesh from an input video using the provided inference script. Model weights will be automatically downloaded on the first run.

### Basic Usage

```bash
python inference/video_to_animated_mesh.py --input assets/examples/davis_camel
```

### Fast Mode

For faster inference (as used in the Hugging Face demo), use the `--fast` flag:

```bash
python inference/video_to_animated_mesh.py --input assets/examples/davis_camel --fast
```

## Citation

If you find ActionMesh useful in your research, please cite:

```bibtex
@misc{sabathier2026actionmeshanimated3dmesh,
      title={ActionMesh: Animated 3D Mesh Generation with Temporal 3D Diffusion}, 
      author={Remy Sabathier and David Novotny and Niloy J. Mitra and Tom Monnier},
      year={2026},
      eprint={2601.16148},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2601.16148}, 
}
```

## License
The weights and code are provided under the license terms found in the [GitHub repository](https://github.com/facebookresearch/actionmesh). Please refer to the LICENSE file there for details.