---
license: gpl-3.0
tags:
  - human-pose-estimation
  - pose-estimation
  - probabilistic
  - computer-vision
datasets:
  - COCO
  - CropCOCO
  - OCHuman
metrics:
  - mAP
  - Ex-mAP
---

# 📦 ProbPose: Probabilistic Human Pose Estimation

ProbPose introduces a probabilistic framework for human pose estimation, focusing on reducing false positives by predicting keypoint presence probabilities and handling out-of-image keypoints. It also introduces the new Ex-OKS metric to evaluate models on false positive predictions.

[![arXiv](https://img.shields.io/badge/arXiv-2412.02254-b31b1b?style=flat)](https://arxiv.org/abs/2412.02254)

[![GitHub repository](https://img.shields.io/badge/GitHub-black?style=flat&logo=github&logoColor=white)](https://github.com/MiraPurkrabek/ProbPose_code)

[![Project Website](https://img.shields.io/badge/Project%20Website-blue?style=flat&logo=google-chrome&logoColor=white)](https://mirapurkrabek.github.io/ProbPose/)



## 📝 Model Details

- **Model type**: ViT-s backbone with ProbPose head
- **Input**: RGB images (192x256)
- **Output**: Coordinates, uncertainties, quality and visibility for human keypoints
- **Language(s)**: Not language-dependent (vision model)
- **License**: GPL-3.0
- **Framework**: MMPose

## 🧠 Training

- **Training data**: [COCO Dataset](https://cocodataset.org/#home)
- **Training script**: [GitHub - ProbPose_code](https://github.com/MiraPurkrabek/ProbPose_code)
- **Epochs**: 210
- **Batch size**: 64
- **Learning rate**: 5e-5
- **Hardware**: 4x NVIDIA A-100

## 📈 Evaluation

- **Metrics**: mAP and Ex-mAP
- With GT bounding boxes

| Dataset  | mAP    | Ex-mAP |
|----------|--------|------- |
| COCO     | 76.6   | 76.4   |
| CropCOCO | 81.7   | 73.9   |
| OCHuman  | 60.4   | 60.2   |

## 📄 Citation

If you use ProbPose in your research, please cite:

```bibtex
@inproceedings{probpose2025,
  title={{ProbPose: A Probabilistic Approach to 2D Human Pose Estimation}}, 
  author={Miroslav Purkrabek and Jiri Matas},
  year={2025},
  booktitle={Computer Vision and Pattern Recognition (CVPR)},
}
```

## 🧑‍💻 Authors

- Miroslav Purkrabek ([personal website](https://github.com/MiraPurkrabek))
- Jiri Matas ([personal website](https://cmp.felk.cvut.cz/~matas/))