In a video demonstration and a paper published in the pre-print journal ArXiv, Samsung researchers show the capabilities of what isdescribed as ‘one-shot’ and ‘few-shot’ machine learning.
The results of their system bring to life popular faces like those of surrealist painterSalvador Dali and actress Marilyn Monroe using a single still image.
The more images that are fed into the program, the more realistic the resulting video becomes.
Though a single image translated into a moving face may look noticeably altered, a sample of 32 images produces a moving picture with near lifelike accuracy.
The newest algorithm was trained using the publicly available VoxCeleb database which has over 7,000 images of celebrities from YouTube videos.
Using that data set, the AI was able to establish what researchers call ‘landmark’ features– universally identifiable traits — among subjects’ noise, eyes, and more.