DepthPro Models
Collection
Depth Pro: Sharp Monocular Metric Depth in Less Than a Second • 9 items • Updated • 14
| B200 | VGA | 720p | 1080p | 4K |
|---|---|---|---|---|
| Throughput (fps) | 95.9 | 20.2 | 5.3 | 0.4 |
| Peak memory (GiB) | 8.3 | 16.3 | 29.5 | 114.6 |
pip install "git+https://github.com/apple-aiml-research/ml-depth-pro-2"
from functools import partial
import torch
from depth_pro_2 import DepthPro2, load_rgb
from depth_pro_2.model import to_normalized_tensor
model = DepthPro2.from_pretrained("apple/DepthPro2-H", precision=torch.bfloat16)
model = model.to("cuda")
transform = partial(to_normalized_tensor, device=torch.device("cuda"))
image, f_px = load_rgb("photo.jpg") # f_px: EXIF focal length, or None
depth = model.infer(transform(image), f_px=f_px)["depth"] # meters, (H, W)
Videos, the other sizes and the command line are on the Depth Pro 2 page.
The weights are released under the Apple Machine Learning Research Model license, for research use only: non-commercial scientific research and academic development.
@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:TODO},
year = {2026},
url = {https://arxiv.org/abs/TODO},
}