README.md

---
license: mit
pipeline_tag: depth-estimation
library_name: pytorch
---

# [CoRL 2025] BEVCalib: LiDAR-Camera Calibration via Geometry-Guided Bird's-Eye View Representation

[![arXiv](https://img.shields.io/badge/arXiv-2506.02587-df2a2a.svg?style=for-the-badge)](https://arxiv.org/abs/2506.02587) 
[![Website](https://img.shields.io/badge/Website-BEVCalib-blue?style=for-the-badge)](https://cisl.ucr.edu/BEVCalib) 
[![Code](https://img.shields.io/badge/Code-BEVCalib-181717.svg?style=for-the-badge&logo=github)](https://github.com/UCR-CISL/BEVCalib)
[![HF Models](https://img.shields.io/badge/%F0%9F%A4%97-Models-yellow?style=for-the-badge)](https://huggingface.co/cisl-hf/BEVCalib) 
[![PyTorch](https://img.shields.io/badge/PyTorch-2.6.0-EE4C2C.svg?style=for-the-badge&logo=pytorch)](https://pytorch.org/get-started/locally/) 
[![License](https://img.shields.io/github/license/TRI-ML/prismatic-vlms?style=for-the-badge)](https://github.com/UCR-CISL/BEVCalib/blob/main/LICENSE)

<!-- Provide a quick summary of what the model is/does. -->

## Introduction

🚗 This model card is for [BEVCALIB: LiDAR-Camera Calibration via Geometry-Guided Bird's-Eye View Representations](https://arxiv.org/abs/2506.02587).

🚀 **All training and inference code are open-sourced now!** Please visit the [project page](https://cisl.ucr.edu/BEVCalib/) and the [Github repo](https://github.com/UCR-CISL/BEVCalib) for details.

💬 **We welcome feedback and look forward to your comments!**

## Download

To download the checkpoints, use the following script.
```
huggingface-cli download cisl-hf/BEVCalib --revision CKPT_VERSION --local-dir YOUR_LOCAL_PATH
```

## Related links

🌐 Website: [https://cisl.ucr.edu/BEVCalib/](https://cisl.ucr.edu/BEVCalib/)

💻 Github: [https://github.com/UCR-CISL/BEVCalib](https://github.com/UCR-CISL/BEVCalib)

📄 Arxiv: [https://arxiv.org/abs/2506.02587](https://arxiv.org/abs/2506.02587)

🤗 HF: [https://huggingface.co/papers/2506.02587](https://huggingface.co/papers/2506.02587)