Learned matcher that pairs SuperPoint keypoints between two images and stops early on easy pairs to save compute.
usyd-community/vitpose-base-simple
Indexed from Hugging FaceLinked to its home on Hugging Face. FrontierOS indexes it; nothing is hosted or mirrored here.ModelPose & keypoints86M paramsEst. Edge GPUEstimated minimum compute for inference: Jetson Orin class, 8–16 GB shared memory. Not a benchmark.Apache 2.0HumanoidMobile baseDesk device
About
Plain vision-transformer model that estimates 2D human body keypoints for each person box produced by a separate detector.
Why it matters for physical AI
Human pose is the input for gesture control, safe human-robot interaction and teleoperation retargeting.
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 usyd-community/vitpose-base-simpleUses the Hugging Face CLI (pip install -U huggingface_hub). This downloads the whole repo; add --include "<pattern>" to fetch only the files you need.