Production Ready Face Re Aging for Visual Effects
Photorealistic digital reaging of faces in video is becoming increasingly common in entertainment and advertising. But the predominant 2D painting workflow often requires framebyframe manual work that can take days to accomplish, even by skilled artists. Although research on facial image reaging has attempted to automate and solve this problem, current techniques are of little practical use as they typically suffer from facial identity loss, poor resolution, and unstable results across subsequent video frames. In this paper, we present the first practical, fullyautomatic and productionready method for reaging faces in video images. Our first key insight is in addressing the problem of collecting longitudinal training data for learning to reage faces over extended periods of time, a task that is nearly impossible to accomplish for a large number of real people. We show how such a longitudinal dataset can be constructed by leveraging the current stateoftheart in facial reaging that, although failing
|
|