Transfiguring portraits
Ira Kemelmacher-Shlizerman · ACM Transactions on Graphics · 2016
People may look dramatically different by changing their hair color, hair style, when they grow older, in a different era style, or a different country or occupation. Some of those may transfigure appearance and inspire creative changes, some not, but how would we know without physically trying? We present a system that enables automatic synthesis of limitless numbers of appearances. A user inputs one or more photos (as many as they like) of his or her face, text queries an appearance of interest (just like they'd search an image search engine) and gets as output the input person in the queried appearance. Rather than fixing the number of queries or a dataset our system utilizes all the relevant and searchable images on the Internet, estimates a doppelgänger set for the inputs, and utilizes it to generate composites. We present a large number of examples on photos taken with completely unconstrained imaging conditions.