While not just being stuck with a photo.
Reference Research Paper : Large Pose 3D Face Reconstruction from a Single Image via Direct Volumetric CNN Regression
Photogrammetry is the science of making measurements from photographs. The input to photogrammetry algorithms are usually photographs, and the output is typically a map, a drawing, a measurement, or a 3D model of some real-world object or scene.
In context, most of the maps you see today are created using a similar process, and aerial images.
Facial 3D reconstruction is a fundamental problem in Computer Vision, and is really quite difficult, mostly because :
The researchers have put left a Convolutional Neural Network to do the feature engineering, from the 2D representation to its 3Dimensional one. I won't dive too deep into how this is done, check out the paper if you're interested.
Read the documentation, of how to run this codebase in the originalreadme.md file.
Generate your own CAD model of the face, slice it up and 3D print it.
Keep a few things in mind :