DepthPro2-focal / README.md
|
Raw History Blame Contribute Delete
3.59 kB
---
license: other
license_name: apple-amlr
license_link: https://github.com/apple-aiml-research/ml-depth-pro-2/blob/main/LICENSE_MODEL
library_name: depth-pro-2
tags:
- focal-length-estimation
- field-of-view
- camera-calibration
- depth-estimation
---
<h1 align="center">Depth Pro 2: Sharp and Temporally Consistent Metric Monocular Depth</h1>
<p align="center">
<a href="https://github.com/apple-aiml-research/ml-depth-pro-2"><img src="https://img.shields.io/badge/GitHub-181717?style=flat-square&amp;logo=github&amp;logoColor=white" alt="GitHub"/></a>
<a href="https://arxiv.org/abs/2611.26603"><img src="https://img.shields.io/badge/Technical%20Report-B31B1B?style=flat-square&amp;logo=arxiv&amp;logoColor=white" alt="Technical Report"/></a>
<a href="https://apple-aiml-research.github.io/ml-depth-pro-2/"><img src="https://img.shields.io/badge/Project%20Page-666666?style=flat-square&amp;logo=data%3Aimage%2Fsvg%2Bxml%3Bbase64%2CPHN2ZyB4bWxucz0iaHR0cDovL3d3dy53My5vcmcvMjAwMC9zdmciIHZpZXdCb3g9IjAgMCAyNCAyNCIgZmlsbD0ibm9uZSIgc3Ryb2tlPSJ3aGl0ZSIgc3Ryb2tlLXdpZHRoPSIyIj48Y2lyY2xlIGN4PSIxMiIgY3k9IjEyIiByPSIxMCIvPjxwYXRoIGQ9Ik0yIDEyaDIwTTEyIDJhMTUgMTUgMCAwIDEgMCAyME0xMiAyYTE1IDE1IDAgMCAwIDAgMjAiLz48L3N2Zz4%3D" alt="Project Page"/></a>
<a href="https://huggingface.co/apple/DepthPro2"><img src="https://img.shields.io/badge/All%20Sizes-FFD21E?style=flat-square&amp;logo=huggingface&amp;logoColor=black" alt="All Sizes"/></a>
</p>
<h3 align="center">Focal length estimator · 23.5M parameters</h3>
## How to use
```bash
pip install "git+https://github.com/apple-aiml-research/ml-depth-pro-2"
```
Load it with any size, for photos and videos without a focal length:
```python
import torch
from huggingface_hub import hf_hub_download
from safetensors.torch import load_file
from depth_pro_2 import DepthPro2
from depth_pro_2.network.fov import FOVEstimator
weights = hf_hub_download("apple/DepthPro2-focal", "model.safetensors")
model = DepthPro2.from_pretrained("apple/DepthPro2-H", precision=torch.bfloat16)
model.fov = FOVEstimator(torch.bfloat16)
model.fov.load_state_dict(load_file(weights))
model = model.to("cuda").eval()
```
On its own, it estimates the focal length of a photo, or one for the frames of a clip:
```python
from functools import partial
import torch
from huggingface_hub import hf_hub_download
from safetensors.torch import load_file
from depth_pro_2 import load_rgb
from depth_pro_2.model import to_normalized_tensor
from depth_pro_2.network.fov import FOVEstimator
weights = hf_hub_download("apple/DepthPro2-focal", "model.safetensors")
fov = FOVEstimator()
fov.load_state_dict(load_file(weights))
fov = fov.to("cuda").eval()
transform = partial(to_normalized_tensor, device=torch.device("cuda"))
image, _ = load_rgb("photo.jpg")
with torch.no_grad():
f_px = fov.focal_length_px(transform(image)[None]) # pixels of the photo; frames (T, 3, H, W)
```
## License
The weights are released under the [Apple Machine Learning Research Model license](https://github.com/apple-aiml-research/ml-depth-pro-2/blob/main/LICENSE_MODEL), for
research use only: non-commercial scientific research and academic development.
## Citation
```bibtex
@article{DepthPro2:2026:arxiv,
title = {Depth Pro 2: Sharp and Temporally Consistent Metric Monocular Depth},
author = {Peiyun Hu and Marko Mihajlovic and Lyndon Duong and Lahav Lipson and Wei Dong and Ama\"{e}l Delaunoy and Stephan R. Richter and Vladlen Koltun},
journal = {arXiv preprint arXiv:2611.26603},
year = {2026},
url = {https://arxiv.org/abs/2611.26603},
}
```