---
library_name: transformers
license: apache-2.0
pipeline_tag: image-text-to-text
tags:
- vision-language-model
- spatial-reasoning
- qwen2_5_vl
---

# GeoSR Model Zoo

This repository hosts the released checkpoints for **GeoSR: Make Geometry Matter for Spatial Reasoning**.

[**Paper**](https://arxiv.org/abs/2603.26639) | [**Project Page**](https://suhzhang.github.io/GeoSR/) | [**Code**](https://github.com/SuhZhang/GeoSR)

## Checkpoints

| Folder | Branch / task | Notes |
| --- | --- | --- |
| `GeoSR3D-Model/` | `static` branch | GeoSR checkpoint for static spatial reasoning |
| `GeoSR4D-Model/` | `dynamic` branch | GeoSR checkpoint for dynamic spatial reasoning |

The model files are stored exactly as exported from our training directories.

## Download

Install the client first if needed:

```bash
pip install -U huggingface_hub
```

Download only the static checkpoint:

```bash
python -c "from huggingface_hub import snapshot_download; snapshot_download(repo_id='SuhZhang/GeoSR-Model', local_dir='data/models', allow_patterns=['GeoSR3D-Model/*'])"
```

Download only the dynamic checkpoint:

```bash
python -c "from huggingface_hub import snapshot_download; snapshot_download(repo_id='SuhZhang/GeoSR-Model', local_dir='data/models', allow_patterns=['GeoSR4D-Model/*'])"
```

Download the whole repository:

```bash
git lfs install
git clone https://huggingface.co/SuhZhang/GeoSR-Model
```

## Usage

In the main GeoSR code repository:

- `static` branch evaluation can use `MODEL_PATH=./data/models/GeoSR3D-Model`
- `dynamic` branch evaluation can use `GEOSR4D_EVAL_MODEL_PATH=../../../data/models/GeoSR4D-Model`

Please refer to the main code repository for full training and evaluation instructions:

- Code: https://github.com/SuhZhang/GeoSR
- Project page: https://suhzhang.github.io/GeoSR/

## Citation

```bibtex
@misc{zhang2026geosr,
  title={Make Geometry Matter for Spatial Reasoning},
  author={Shihua Zhang and Qiuhong Shen and Shizun Wang and Tianbo Pan and Xinchao Wang},
  year={2026},
  eprint={2603.26639},
  archivePrefix={arXiv},
  primaryClass={cs.CV},
  url={https://arxiv.org/abs/2603.26639}
}
```