---
base_model:
- Qwen/Qwen3-VL-4B-Instruct
license: apache-2.0
pipeline_tag: depth-estimation
library_name: transformers
tags:
- vision-language-model
- depth-estimation
- 3d-vision
- multimodal
- qwen3-vl
---

Update 2026-05-18 (v1.0): Initial release

# DepthVLM-4B

DepthVLM serves as a unified foundation model for both low-level dense geometry prediction and high-level multimodal understanding, while achieving substantially faster inference compared with existing VLM-based approaches such as DepthLM and Youtu-VL.

By attaching a lightweight depth head to the LLM backbone and training under a unified vision-text supervision paradigm, DepthVLM transforms a single VLM into a native dense geometry predictor while preserving its multimodal capability.

## Highlights

- **Native dense metric depth estimation in VLMs**: Directly predicts geometry within the VLM framework.
- **Unified multimodal understanding and geometry prediction**: Generates full-resolution depth maps alongside language outputs in a single forward pass.
- **Efficient Inference**: Achieves higher efficiency compared to per-pixel query or coarse token-level outputs.
- **Versatile Application**: Supports both indoor and outdoor metric depth estimation.
- **Improved 3D spatial reasoning**: Moving toward a truly unified foundation model.

## Resources

- **Paper:** [Unlocking Dense Metric Depth Estimation in VLMs](https://arxiv.org/abs/2605.15876)
- **Project Page:** [https://depthvlm.github.io/](https://depthvlm.github.io/)
- **Repository:** [https://github.com/hanxunyu/DepthVLM](https://github.com/hanxunyu/DepthVLM)

## Usage

Please refer to the official repository for detailed instructions on:

- Data preprocessing  
- Training  
- Evaluation  
- Inference and visualization  

## Citation

If you find this work useful, please cite:

```bibtex
@article{yu2026unlocking,
  title={Unlocking Dense Metric Depth Estimation in VLMs},
  author={Hanxun Yu and Xuan Qu and Yuxin Wang and Jianke Zhu and Lei Ke},
  journal={arXiv preprint arXiv:2605.15876},
  year={2026}
}
```