Apple unveils Depth Pro 2: sharp, metrically accurate, temporally consistent monocular depth
Apple ML Research · rss · 2026-11-20
Apple's ML research team presents Depth Pro 2, an approach to dense metric depth estimation for images and video at full resolution:
- Key finding: prior monocular depth methods commonly trade off temporal consistency against boundary sharpness — multi-frame methods favor consistency, single-frame methods favor sharpness.
- Approach: a single, scalable network trained to process both images and video, predicting depth maps at native resolution.
- Results: metric accuracy, sharpness, and temporal consistency all at once, outperforming prior methods on the dimensions they usually sacrifice.
Directly relevant to robotics, AR, and video generation pipelines that need stable depth signals.
More from Multimodal
- LTX 2.5 keeps crashing on AMD 9070 XT with driver timeouts while MiniMax H3 runs fine — ZestycloseReading504 · 2026-11-22
- Stripe residency dev draws all friends in JavaScript with GPT 6.2 Astra, results stun — gabrielchua · 2026-11-22
- Fable 5.2 plus WebGL demoed as a tool to "create anything" — hewarsaber · 2026-11-22
- Cinematic UFO folklore music video built with Suno and SLOPCANNON — DarkroomSignal · 2026-11-22
- Photographer crafts AI-generated digital muse Nous Girl on faux magazine cover — alexcovo_eth · 2026-11-22
- Turn any Google Maps location into a cinematic drone shot with AI — aziz4ai · 2026-11-22