--- language: - en license: other pipeline_tag: image-to-3d tags: - video-to-4D arxiv: 2601.16148 python_version: '3.11' --- # 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.