apple-aiml-research/ml-depth-pro-2
Model
Can I trust it?
Be careful with this one.
Stars from real accounts No data
We haven't checked its stars for fakes yet.
Active OK
Last change 2 days ago.
Licence Careful
No licence: legally you can't reuse the code, unless the README says otherwise.
Quick checks from public data. They help, but they are no guarantee.
What it is
A research repository with code to run Depth Pro 2, a model that estimates metric depth in meters for every pixel of a photo, video or live camera feed. The depth is sharp at object edges and stable across video frames. It provides four model sizes with downloadable weights and…
Who it's for
Computer vision researchers and Python developers who need per-pixel metric depth from monocular photos or video
How to use it
Install
uv run depth-pro-2 predict -i assets/example.jpg -o out/From its README. Check it there before running it.
Ask your AI to set it up
Paste this into Claude, ChatGPT or your coding assistant.
Help me install and set up apple-aiml-research/ml-depth-pro-2 in my project. Follow its README: https://github.com/apple-aiml-research/ml-depth-pro-2. Explain each step and check it is safe before running anything.
Star curve
On the radar
Its place among the radar's top 100, day by day, with #1 at the top. Gaps are days it was out of the top 100.
Records
- Best place on RepoAlerts: #46, on 21 Nov 2026
Alternatives
Similar projects named in its profile. Each link searches the directory.
Get alerts for repos like this
We'll email you when something in Models & inference starts rising. Free, once a week, only what matches.
What arrives: one email on Mondays with the repos that match, never more. See last week's. Privacy
For maintainers
Add this badge to your README. It shows the repo's place on the radar, updates every hour and links back to this page.
[](https://repoalerts.com/repo/apple-aiml-research/ml-depth-pro-2?ref=badge)Similar repos
- aryamandarda/tamserve
A serving engine for live multi-camera object tracking with SAM 2, SAM 2.1 and EdgeTAM. One shared model copy tracks objects across many camera feeds at once, and a Tracker can find and follow objects
- ReLift3D/ReLift
Research code for ReLift, a method that lifts every pixel of a video into 3D trajectories by combining a dense 2D point tracker with a video 3D geometry model. A small transformer corrector repairs an
- apple-aiml-research/ml-fastframes
Official implementation of FastFrames, two autoregressive two-step video diffusion models (1.3B and 14B) that generate 480p video at interactive latency, plus an optimized, camera-controllable version
- amanikiruga/UGG
Official repository for UGG, a video diffusion model fine-tuned from Wan2.2-TI2V-5B that jointly predicts RGB frames, depth and camera rays. It provides a Python inference API for six tasks (video, im
- escudero/brandpose
Personal research project that estimates where shoppers look in a store from an ordinary fixed security camera. It chains YOLO11 for person detection and tracking, Gaze-LLE for gaze estimation, and De
- kornia/kornia
Differentiable computer vision library built on PyTorch, providing image processing operators, geometric vision algorithms, robust estimation, local feature matching and batched augmentations that run