metadata
license: apache-2.0
tags:
- onnx
- mediapipe
- face-landmarks
- face-mesh
- qtmesheditor
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.