Face Mesh V2 landmark model (ONNX)

Google MediaPipe's Face Landmarks Detector (Face Mesh V2), converted to ONNX.

Input [N,256,256,3] RGB in [0,1] — the rotated, cropped face ROI.
Outputs [N,1,1,1434] = 478 landmarks × (x,y,z) in 256-crop pixels, plus a face-presence logit. Landmarks project back through the inverse ROI transform; a 146-landmark subset feeds the blendshape model.

License

Apache-2.0 — this graph is a direct ONNX conversion of a Google MediaPipe model (Apache-2.0 code AND weights). Conversion + numerical-parity proof (vs the Python mediapipe reference): scripts/export-facecap-onnx.py, contract in docs/MOCAP_SPIKE.md.

How it is used

Mirror of one graph from fernandotonon/QtMeshEditor-models (mocap/…), which QtMeshEditor downloads on first use for its Performance Capture feature (video/webcam → facial morph + head + full-body skeletal animation, epic #869). This standalone repo is for discoverability; the app fetches from the aggregate repo.

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support