sapiens
sapiens2
human-centric
vision-transformer
sapiens2 / README.md
rawalkhirodkar's picture
Update model card
2acbac6 verified
---
license: other
license_name: sapiens2-license
license_link: https://github.com/facebookresearch/sapiens2/blob/main/LICENSE.md
library_name: sapiens
tags:
- sapiens
- sapiens2
- human-centric
- vision-transformer
---
# Sapiens2
Sapiens2 is a family of high-resolution vision transformers pretrained on **1 billion human images** β€” designed for human-centric tasks such as pose estimation, body-part segmentation, surface normals, and pointmaps.
This is the **index** repository: each variant lives in its own model repo (linked below).
- πŸ“„ **Paper:** [arXiv:2604.21681](https://arxiv.org/pdf/2604.21681)
- 🌐 **Project Page:** [rawalkhirodkar.github.io/sapiens2](https://rawalkhirodkar.github.io/sapiens2)
- πŸ’» **Code:** [github.com/facebookresearch/sapiens2](https://github.com/facebookresearch/sapiens2)
- πŸ“š **Collection:** [Sapiens2 on HuggingFace](https://huggingface.co/collections/facebook/sapiens2)
## Pretrained Backbones
| Model | Params | Repository |
|-------|--------|------------|
| Sapiens2-0.1B | 0.114 B | [facebook/sapiens2-pretrain-0.1b](https://huggingface.co/facebook/sapiens2-pretrain-0.1b) |
| Sapiens2-0.4B | 0.398 B | [facebook/sapiens2-pretrain-0.4b](https://huggingface.co/facebook/sapiens2-pretrain-0.4b) |
| Sapiens2-0.8B | 0.818 B | [facebook/sapiens2-pretrain-0.8b](https://huggingface.co/facebook/sapiens2-pretrain-0.8b) |
| Sapiens2-1B | 1.462 B | [facebook/sapiens2-pretrain-1b](https://huggingface.co/facebook/sapiens2-pretrain-1b) |
| Sapiens2-1B (4K) | 1.607 B | [facebook/sapiens2-pretrain-1b-4k](https://huggingface.co/facebook/sapiens2-pretrain-1b-4k) |
| Sapiens2-5B | 5.071 B | [facebook/sapiens2-pretrain-5b](https://huggingface.co/facebook/sapiens2-pretrain-5b) |
## Task Checkpoints
### Pose Estimation
| Model | Repository |
|-------|------------|
| Sapiens2-0.4B | [facebook/sapiens2-pose-0.4b](https://huggingface.co/facebook/sapiens2-pose-0.4b) |
| Sapiens2-0.8B | [facebook/sapiens2-pose-0.8b](https://huggingface.co/facebook/sapiens2-pose-0.8b) |
| Sapiens2-1B | [facebook/sapiens2-pose-1b](https://huggingface.co/facebook/sapiens2-pose-1b) |
| Sapiens2-5B | [facebook/sapiens2-pose-5b](https://huggingface.co/facebook/sapiens2-pose-5b) |
### Body-Part Segmentation
| Model | Repository |
|-------|------------|
| Sapiens2-0.4B | [facebook/sapiens2-seg-0.4b](https://huggingface.co/facebook/sapiens2-seg-0.4b) |
| Sapiens2-0.8B | [facebook/sapiens2-seg-0.8b](https://huggingface.co/facebook/sapiens2-seg-0.8b) |
| Sapiens2-1B | [facebook/sapiens2-seg-1b](https://huggingface.co/facebook/sapiens2-seg-1b) |
| Sapiens2-5B | [facebook/sapiens2-seg-5b](https://huggingface.co/facebook/sapiens2-seg-5b) |
### Surface Normal Estimation
| Model | Repository |
|-------|------------|
| Sapiens2-0.4B | [facebook/sapiens2-normal-0.4b](https://huggingface.co/facebook/sapiens2-normal-0.4b) |
| Sapiens2-0.8B | [facebook/sapiens2-normal-0.8b](https://huggingface.co/facebook/sapiens2-normal-0.8b) |
| Sapiens2-1B | [facebook/sapiens2-normal-1b](https://huggingface.co/facebook/sapiens2-normal-1b) |
| Sapiens2-5B | [facebook/sapiens2-normal-5b](https://huggingface.co/facebook/sapiens2-normal-5b) |
### Pointmap Estimation
| Model | Repository |
|-------|------------|
| Sapiens2-0.4B | [facebook/sapiens2-pointmap-0.4b](https://huggingface.co/facebook/sapiens2-pointmap-0.4b) |
| Sapiens2-0.8B | [facebook/sapiens2-pointmap-0.8b](https://huggingface.co/facebook/sapiens2-pointmap-0.8b) |
| Sapiens2-1B | [facebook/sapiens2-pointmap-1b](https://huggingface.co/facebook/sapiens2-pointmap-1b) |
| Sapiens2-5B | [facebook/sapiens2-pointmap-5b](https://huggingface.co/facebook/sapiens2-pointmap-5b) |
## License
Released under the [Sapiens2 License](https://github.com/facebookresearch/sapiens2/blob/main/LICENSE.md).
## Citation
```bibtex
@article{khirodkarsapiens2,
title={Sapiens2},
author={Khirodkar, Rawal and Wen, He and Martinez, Julieta and Dong, Yuan and Su, Zhaoen and Saito, Shunsuke},
journal={arXiv preprint arXiv:2604.21681},
year={2026}
}
```