Add pipeline tag and improve model card

README.md

@@ -1,36 +1,55 @@
 ---
-tags:
-- video-to-4D
-license: other
-python_version: "3.11"
 language:
 - en
+license: other
+pipeline_tag: image-to-3d
+tags:
+- video-to-4D
+arxiv: 2601.16148
+python_version: '3.11'
 ---
 
-<div align="center">
-<h1>ActionMesh: Animated 3D Mesh Generation with Temporal 3D Diffusion</h1>
+# ActionMesh: Animated 3D Mesh Generation with Temporal 3D Diffusion
 
-<a href="https://remysabathier.github.io/actionmesh/"><img src="https://img.shields.io/badge/Project_Page-green" alt="Project Page"></a>
+[**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.
 
-**[Meta Reality Labs](https://ai.facebook.com/research/)**; **[University College London, UCL](https://geometry.cs.ucl.ac.uk/index.php)**; **[SpAItial](https://www.spaitial.ai/)**
+[[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)]
 
-[Remy Sabathier](https://remysabathier.github.io/RemySabathier/), [David Novotny](https://d-novotny.github.io/), [Niloy J. Mitra](http://www0.cs.ucl.ac.uk/staff/n.mitra/), [Tom Monnier](https://tmonnier.com/)
-</div>
+## Installation
 
-## Overview
+ActionMesh requires an NVIDIA GPU with at least 32GB VRAM.
 
-ActionMesh is a fast video to animated mesh model with unprecedented quality. Generate animated mesh seamlessly importable into any 3D software in less than a minute.
+```bash
+git clone https://github.com/facebookresearch/actionmesh.git
+cd actionmesh
+git submodule update --init --recursive
+pip install -r requirements.txt
+pip install -e .
+```
 
-## License
+## Quick Start
 
-See the LICENSE file for details about the license under which this repository is made available.
+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.
 
-## Quick Start
+### Basic Usage
+
+```bash
+python inference/video_to_animated_mesh.py --input assets/examples/davis_camel
+```
 
-Please refer to our [Github Repo](https://github.com/facebookresearch/actionmesh)
+### 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},
@@ -40,4 +59,7 @@ Please refer to our [Github Repo](https://github.com/facebookresearch/actionmesh
       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.