A Morphable Model for the Synthesis of 3D Faces
The above video is over 12 years old. How was the software done?
I need something way simpler but basically the same: a morphable model (thorax) that can be altered after being pre-morphed using a picture.
Any links that might provide useful information are appreciated.
Are there any open source projects that might have helpful code that could be studied?
A 3D Morphable Model (3DMM) is a statistical object model separating shape from appearance variation. Typically, 3DMMs are used as a statistical prior in computer graphics and vision. A model is learned from high-quality 3D scans of multiple object instances.
A 3D Morphable Face Model is a generative model for face shape. and appearance that is based on two key ideas: First, all faces are. in dense point-to-point correspondence, which is usually estab- lished on a set of example faces in a registration procedure and then. maintained throughout any further processing steps.
3D Morphable Model (3DMM) is a statistical model of. 3D facial shape and texture in a space where there are ex- plicit correspondences [4].
The Basel Face Model They are generative shape models, and as such applicable in image analysis and synthesis tasks. 3D Morphable Models, and specifically 3D Morphable Face Models are the core of the research in the Computer Vision Group at the University of Basel.
The details are all in their paper:
www.mpi-inf.mpg.de/~blanz/html/data/morphmod2.pdf
In short, you need:
Note that their choice of the name 'Morphable Model' is misleading. They are referring to something much more specific than a set of difference morphs or morph targets.
What you need is called Morph target animation. Blender implements this, but the feature is called Shape Keys.
You can see an example of morphing at NeHe Productions.
This process works by creating a base vector of points, such as a face and a set of change vectors that contain the differences to various morph targets. A possible morph target would be smile and it would contain the offset values that added to the original face would result in a smiling face.
You can do linear combinations of morph targets and you can even create caricatures, by exaggerating the factors (original + 2*smile).
If you love us? You can donate to us via Paypal or buy me a coffee so we can maintain and grow! Thank you!
Donate Us With