apple/ml-depth-pro

Health v2 · maintenance only

Flags: no_releases no_license

Adoption not part of the score

5737 stars · 432 forks observed · 2026-10-07

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

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

library · maturity active

machine-learning deep-learning computer-vision image-processing computer-vision machine-learning deep-learning artificial-intelligence python cli monocular-depth-estimation depth-maps metric-depth zero-shot focal-length-estimation vision-transformer research-model gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="apple-aiml-research/ml-depth-pro")