█

AI/TLDR

Apple · 2026-11-19 · notable

Depth Pro 2 — Apple's open depth model for sharp, steady video depth

In short

Apple's Depth Pro 2 estimates metric depth in meters for photos, video and live camera feeds at full resolution. It ships in four sizes, from 24M to 872M parameters, with code and research-only weights.

Apple · 2026-11-19 · 4 sources checked

Preview image from Apple's Depth Pro 2 project page

One Apple network gives depth maps that are both sharp at object edges and steady from frame to frame.

What is it?

Depth Pro 2 is the successor to Apple's Depth Pro: a family of models that predicts how far away every pixel is, in meters, from an ordinary photo, a video or a live feed. It comes in S (24M), B (97M), L (334M) and H+ (872M) sizes, plus a shared 23.5M focal-length estimator for when the camera's focal length is unknown, and sits in the Hugging Face trending top 10.

How does it work?

A multi-view transformer reads one or more frames together. After the first third of its blocks it alternates attention inside each frame with attention across frames, and a DPT decoder then predicts an inverse depth map for every frame at native resolution.

Why does it matter?

The paper argues that earlier depth models forced a choice: multi-frame methods stay consistent over time, single-frame methods keep edges sharp. Apple reports that Depth Pro 2 beats both kinds on boundary sharpness and jitter across the Sintel and Spring benchmarks. The weights are licensed for non-commercial research only.

Who is it for?

computer vision researchers, 3D and video effects developers

Try it

uv run depth-pro-2 predict -i assets/example.mp4 -o out/

Sources · 4 outlets

Tags

  • apple
  • depth-pro-2
  • depth-estimation
  • metric-depth
  • monocular-depth
  • video-depth
  • computer-vision
  • open-weights
  • coreml

← All releases · Learn AI