# apple/ml-depth-pro

Depth Pro: Sharp Monocular Metric Depth in Less Than a Second.

Repository: https://github.com/apple/ml-depth-pro
Canonical: https://ross.abutalabs.com/products/ml-depth-pro
Language: Python
License: NOASSERTION
License Family: other
Last push: 2025-04-21T12:13:43+00:00

## Health v2 (maintenance only)
Score: 30/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 17, release rhythm 35, longevity 52
- inputs: {"age_days": 737, "days_push": 499, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 5683, forks 429 (observed 2026-08-28T04:09:27.864365+00:00)

## What it is
Depth Pro is Apple's reference implementation of a foundation model for zero-shot metric monocular depth estimation, producing sharp high-resolution depth maps with absolute scale from a single image in under a second on a GPU. It includes a Python package, a command-line runner, pretrained checkpoints, and boundary-focused evaluation metrics.

## Use cases
- estimate metric depth maps from a single photo
- generate high-resolution depth maps for 3D reconstruction
- estimate camera focal length from one image
- evaluate boundary accuracy of predicted depth maps
- run depth prediction from the command line on images
- integrate depth estimation into a Python pipeline

## When to choose
- you need fast, sharp, metric depth maps from single images without camera metadata
- you want a zero-shot depth model with pretrained checkpoints
- you need focal length estimation alongside depth prediction

## When to avoid
- you need real-time depth on CPU-only hardware
- you need a permissively licensed model for commercial use without checking the custom license
- you need stereo or multi-view depth estimation

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, deep-learning, computer-vision, image-processing
- domain: computer-vision, machine-learning, deep-learning, artificial-intelligence
- platform: python, cli
- tags: monocular-depth-estimation, depth-maps, metric-depth, zero-shot, focal-length-estimation, vision-transformer, research-model, gpu

## Member repositories
- apple/ml-depth-pro (main) score 30

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:27.864365+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:54:14.748233+00:00, confidence not recorded.
  - readme: https://github.com/apple/ml-depth-pro (fetched 2026-08-28T04:09:27.864365+00:00, sha ec6f272ab9f0)
- Data as of 2026-08-30T08:39:29.467469+00:00.