Lightweight monocular model that predicts a relative depth map from a single RGB frame.
apple/DepthPro-hf
Indexed from Hugging FaceLinked to its home on Hugging Face. FrontierOS indexes it; nothing is hosted or mirrored here.ModelDepth estimation952M paramsEst. 24 GB GPUEstimated minimum compute for inference: Desktop GPU with about 24 GB of memory. Not a benchmark.Apple ML ResearchMobile baseSingle armHumanoid
About
Apple's monocular model that outputs sharp metric depth plus an estimated focal length from one image, with no camera intrinsics needed.
Why it matters for physical AI
Metric depth from an uncalibrated camera is handy for offline mapping and for labeling robot datasets.
Summary written by FrontierOS in our own words. The upstream card and license govern use. Metadata checked 27 Sep 2026. Read the full card on Hugging Face
Files, weights and version history live on Hugging Face. FrontierOS indexes this repo; it does not host or mirror it.
hf download apple/DepthPro-hfUses the Hugging Face CLI (pip install -U huggingface_hub). This downloads the whole repo; add --include "<pattern>" to fetch only the files you need.