README.md

---
license: cc-by-nc-sa-4.0
pipeline_tag: image-to-3d
---

# Human3R: Everyone Everywhere All at Once

Human3R is a unified, feed-forward framework for online 4D human-scene reconstruction, in the world frame, from casually captured monocular videos. It jointly recovers global multi-person SMPL-X bodies ("everyone"), dense 3D scene ("everywhere"), and camera trajectories in a single forward pass ("all-at-once").

TL;DR: Inference with One model, One stage; Training in One day using One GPU

*   **Paper**: [Human3R: Everyone Everywhere All at Once](https://huggingface.co/papers/2510.06219)
*   **Project Page**: [https://fanegg.github.io/Human3R/](https://fanegg.github.io/Human3R/)
*   **Code**: [https://github.com/fanegg/Human3R](https://github.com/fanegg/Human3R)

<div align="center">
<img src="https://github.com/user-attachments/assets/47fc7ecf-5235-471c-84b9-ccfeca6d56ea" alt="Human3R Demo" width="100%">
</div>

## Sample Usage

To run the inference demo, you can use the following command (assuming you have followed the installation steps from the [GitHub repository](https://github.com/fanegg/Human3R)):

```bash
# input can be a folder or a video
# the following script will run inference with Human3R and visualize the output with viser on port 8080
CUDA_VISIBLE_DEVICES=0 python demo.py --model_path MODEL_PATH --size 512 \
    --seq_path SEQ_PATH --output_dir OUT_DIR --subsample 1 --use_ttt3r \
    --vis_threshold 2 --downsample_factor 1 --reset_interval 100

# Example:
CUDA_VISIBLE_DEVICES=0 python demo.py --model_path src/human3r.pth --size 512 --seq_path examples/GoodMornin1.mp4 --subsample 1 --use_ttt3r --vis_threshold 2 --downsample_factor 1 --reset_interval 100 --output_dir tmp
```
Output results will be saved to `output_dir`.

## Citation

If you find our work useful, please cite:

```bibtex
@article{chen2025human3r,
    title={Human3R: Everyone Everywhere All at Once},
    author={Chen, Yue and Chen, Xingyu and Xue, Yuxuan and Chen, Anpei and Xiu, Yuliang and Gerard, Pons-Moll},
    journal={arXiv preprint arXiv:2510.06219},
    year={2025}
    }
```