Home -> Projects ->Hallucinating Faces Member Login  

Jump to: Publications | Releases


We have developed an algorithm that can be used to learn a prior on the spatial distribution of the image gradient for frontal images of faces. We have shown how such a prior can be incorporated into a super-resolution algorithm to yield 4-8 fold improvements in resolution (16-64 times as many pixels) using as few as 2-3 images. The additional pixels are, in effect, hallucinated.

 Related Publications

We grant permission to use and publish all data and results from this site, provided the following paper is referenced:

 Releases [ Public ]