Illumination-Aware Age Progression
AbstractExample Results , see data and files for comparison below.
CBS Innovation nation did a great episode about our software: check it out here!; full episode.
We present an approach that takes a single photograph of a child as input and automatically produces a series of age-progressed outputs between 1 and 80 years of age, accounting for pose, expression, and illumination. Leveraging thousands of photos of children and adults at many ages from the Internet, we first show how to compute average image subspaces that are pixel-to-pixel aligned and model variable lighting. These averages depict a prototype man and woman aging from 0 to 80, under any desired illumination, and capture the differences in shape and texture between ages. Applying these differences to a new photo yields an age progressed result. Contributions include relightable age subspaces, a novel technique for subspace-to-subspace alignment, and the most extensive evaluation of age progression techniques in the literature.
FilesPaper: pdf appeared at IEEE Conf. on Computer Vision and Pattern Recognition (CVPR) 2014
Citation to the paper at google scholar: bibtex
Additional results and experiments: pdf
The FGNET Database that we used for comparisons: FGNET zip by Andreas Lanitis
Htmls of our Amazon Mechanical Turk tasks used for evaluation: Htmls for Mechanical Turk.
Our results on all the FGNET photos: FGNET age progression results (193Mb)
Please let us know if you compare to our results, and cite the paper.
ResultsBelow are many examples of our automatic age progression. For each example, we show the input (left) and automatically "aged" version of the input using our method (right). Age is specified below each photo.
ComparisonA single photo of a child (far left) is age progressed (left in each pair) and compared to photos of the same person at the corresponding age (right in each pair). The age progressed face is composited into the ground truth photo to match the hairstyle and background (see supplementary material for comparisons of just the face regions).
MorphsVideo on YouTube
Left image is the starting input photo, and right image will transform to age 80 to show our automatic aging process.
AcknowledgementsWe thank Google and Intel for supporting this research and "Thunder" for allowing us to use his photo collection for comparisons.
NBC's Today Show | KOMO News | KUOW/NPR | KING5 | KIRO TV
ContactFor more information please contact: Ira Kemelmacher-Shlizerman