Audio-Based Caricature Exaggerations (new patent)


‘Caricaturization’ (the act of making a caricature of someone/something) can now be performed automatically – and not only that, it can be set to music. Matan Sela and colleagues at Prof. Ron Kimmel’s Geometric Image Processing Lab, Technion – Israel Institute of Technology, have developed ‘A novel caricature generation framework for surfaces’. Computer Vision and Image Understanding 141 (2015) 1–17.

“The method scales the gradient fields of the surface coordinates by a function of the Gaussian curvature of the surface, and solves a corresponding Poisson equation for finding the exaggerated shape. When a reference shape is provided, local discrepancies are used to amplify the scaling effect, while in the absence of a reference shape, the reference is assumed to be a scaled down version of the given one thereby letting the Gaussian curvature define the relative stretch.”

Their ‘caricaturization’ algorithm can also tweak the ‘caricaturization’ levels in sync with an audio input [as in the above video], a procedure for which the team have just received a US patent. See: Audio-Based Caricature Exaggeration

Note: The patent points out that the technique is not restricted to human heads – it can also be applied to animals, mythical creatures, &etc.