README.md

---
license: other
license_name: multiple-licenses
license_link: https://huggingface.co/AntResearch/4DAnyone/blob/main/LICENSE
pipeline_tag: video-to-video
tags:
  - video-generation
  - multiview-video-generation
  - 4D-human-reconstruction
  - novel-view-synthesis
---

# 4DAnyone: Create Anyone in 4D from a Casual Monocular Video

[Project Page](https://4danyone.github.io/)  |  [Paper](https://arxiv.org/abs/2608.20335)  |  [Code](https://github.com/ant-research/4DAnyone)

<img src="assets/teaser.gif" width="100%" alt="4DAnyone teaser">

4DAnyone turns a casual monocular video into multi-view videos, enabling downstream 4DGS reconstruction.

## Models

```text
4danyone/
├── model.safetensors
├── smplx_to_goliath70.pt
├── Wan2.2_VAE.pth
├── models_t5_umt5-xxl-enc-bf16.pth
└── umt5-xxl/
    ├── special_tokens_map.json
    ├── spiece.model
    ├── tokenizer.json
    └── tokenizer_config.json

gvhmr/
├── gvhmr_siga24_release.ckpt
├── epoch=10-step=25000.ckpt
├── vitpose-h-multi-coco.pth
└── yolov8x.pt

data/source/pexels/
└── eight 121-frame example videos
```

Licensing is asset-specific. See [LICENSE](LICENSE) for the exact scope and
[licenses/](licenses/) for the complete terms.

## Citation

If you find 4DAnyone useful or interesting, please cite our work and give this model a ❤️ like:

```bibtex
@article{jin2026fdanyone,
  title={4DAnyone: Create Anyone in 4D from a Casual Monocular Video},
  author={Jin, Yudong and Xie, Tao and Zhang, Qihang and Shen, Zehong and Xu, Zhen and Shen, Yujun and Bao, Hujun and Zhou, Xiaowei and Xu, Yinghao},
  journal={arXiv preprint arXiv:2608.20335},
  year={2026},
  url={https://arxiv.org/abs/2608.20335}
}
```