---
license: cc-by-nc-4.0
base_model: Qwen/Qwen3-VL-4B-Instruct
pipeline_tag: image-text-to-text
library_name: transformers
language:
  - en
tags:
  - remote-sensing
  - visual-grounding
  - horizontal-bounding-box
  - oriented-bounding-box
  - reinforcement-learning
  - qwen3-vl
---

<div align="center">

<h1 align="center">GeoBox-R1: Curriculum-Guided SFT and Geometric RL for Unified Box-Level Remote Sensing Visual Grounding</h1>

Chenxi Lan\*, Yuchen Wu\*, Minghang Zhou, Tianyu Li, Zhihao Qiu, Guoqing Wang<sup>†</sup>

<sup>\*</sup>Equal contribution &nbsp;&nbsp; <sup>†</sup>Corresponding author

*Under review at AAAI 2027*

[Project page](https://yuchenwu73.github.io/geobox-r1/) · [Code](https://github.com/yuchenwu73/GeoBox-R1)

</div>

## Overview

GeoBox-R1 is a 4B vision-language model for unified remote-sensing visual grounding. Given an
aerial or satellite image and a referring expression, the same model can produce either a
horizontal bounding box (HBB) or an oriented bounding box (OBB).

The model starts from Qwen3-VL-4B-Instruct and is trained in two stages:

1. **Curriculum-guided SFT** orders examples from HBB grounding to OBB grounding and then
   HBB-to-OBB chain-of-thought reasoning.
2. **Geometric RL (GDPO)** improves geometric precision with rotated-IoU and adaptive
   Wasserstein rewards, without a learned reward model.

## Results

Macro averages are shown below. Full comparisons, per-dataset results, and the evaluation
protocol are available on the [project page](https://yuchenwu73.github.io/geobox-r1/).

| Task | Evaluation sets | Acc@0.5 | Acc@0.7 | mIoU / mRIoU |
| --- | :-: | :-: | :-: | :-: |
| HBB | 7 | **58.78** | **42.22** | **50.39** |
| OBB | 3 | **47.32** | **27.55** | **39.85** |

Among the evaluated baselines, GeoBox-R1 achieves the best macro averages while using 4B
parameters. GDPO is trained only on OBB samples, but it also improves HBB performance over the
SFT stage.

## Usage

Install a recent Transformers release together with PyTorch, Pillow, and Accelerate, then run:

````python
from PIL import Image
from transformers import AutoModelForImageTextToText, AutoProcessor

model_id = "yuchenwu73/GeoBox-R1"

model = AutoModelForImageTextToText.from_pretrained(
    model_id,
    dtype="auto",
    device_map="auto",
)
processor = AutoProcessor.from_pretrained(model_id)

image = Image.open("scene.png").convert("RGB")
expression = "the brown SUV on the right"

prompt = f"""Locate the instance that matches the description: [{expression}]. Report oriented bbox coordinates in following JSON format:
```json
[
\t{{"oriented_bbox": [[x1, y1], [x2, y2], [x3, y3], [x4, y4]]}}
]
```"""

messages = [
    {
        "role": "user",
        "content": [
            {"type": "image"},
            {"type": "text", "text": prompt},
        ],
    }
]
text = processor.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
)
inputs = processor(text=[text], images=[image], return_tensors="pt").to(model.device)

generated = model.generate(**inputs, max_new_tokens=256)
generated = generated[:, inputs.input_ids.shape[1]:]
print(processor.batch_decode(generated, skip_special_tokens=True)[0])
````

For HBB grounding, replace the prompt with:

````python
prompt = f"""Locate the instance that matches the description: [{expression}]. Report horizontal bbox coordinates in following JSON format:
```json
[
\t{{"horizontal_bbox": [x1, y1, x2, y2]}}
]
```"""
````

Coordinates are quantized to `[0, 1000]`. Multiply x coordinates by the image width divided by
1000, and y coordinates by the image height divided by 1000, to recover pixel coordinates.

The repository also provides evaluation scripts, an interactive demo, and the complete training
pipeline: [github.com/yuchenwu73/GeoBox-R1](https://github.com/yuchenwu73/GeoBox-R1).

## License

The model weights are released under the **CC BY-NC 4.0** license. Users must also comply with
the licenses and terms of the underlying Qwen3-VL model and any input datasets they use.

## Citation

```bibtex
@misc{geoboxr1,
  title  = {GeoBox-R1: Curriculum-Guided SFT and Geometric RL for
            Unified Box-Level Remote Sensing Visual Grounding},
  author = {Lan, Chenxi and Wu, Yuchen and Zhou, Minghang and
            Li, Tianyu and Qiu, Zhihao and Wang, Guoqing},
  year   = {2026},
  url    = {https://yuchenwu73.github.io/geobox-r1/},
  note   = {Preprint}
}
```