anilbas/3DMMasSTN

MatConvNet implementation for incorporating a 3D Morphable Model (3DMM) into a Spatial Transformer Network (STN)

47
/ 100
Emerging

This project helps researchers and developers working with facial image analysis to normalize diverse human faces. It takes a single 2D image of a face and outputs a 'flattened' 2D image where the face is geometrically corrected, removing variations caused by pose changes or self-occlusions. The system learns to fit a 3D morphable model to the face without needing pre-labeled examples. This is ideal for specialists in computer vision, biometrics, and graphics who need a standardized facial representation.

285 stars. No commits in the last 6 months.

Use this if you need to process many 2D facial images and want a consistent, normalized 'texture map' of each face, regardless of their original pose or expression, for further analysis like identity recognition or attribute estimation.

Not ideal if you are looking for a ready-to-use application or a model for general image classification, as this is a framework for advanced facial normalization within a research context.

facial image analysis computer vision research face normalization 3D face modeling biometric image processing
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 21 / 25

How are scores calculated?

Stars

285

Forks

50

Language

Matlab

License

Apache-2.0

Last pushed

Apr 15, 2018

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/anilbas/3DMMasSTN"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.