A group of researchers at Microsoft have made a new app allows users to convert photographs into caricatures. The group included Stanford graduate Kaidi Cao, Microsoft’s Lu Yuan, and Jing Liao from the City University of Hong Kong who came together to develop an AI that could convert photos into caricatures.
The trio used over a thousand different photos to train the AI in order to convert them to caricatures. The AI uses Generative Adversarial Networks (GANs) to generate the caricature. The first one looks at the geometry of the face to create the base model, while the second one applies an artistic texture to the model to give it the hand-drawn look. The researchers are expected to unveil the project next month at SIGGRAPH Asia in Tokyo.
The results sure aren’t perfect but will improve as the AI learns better. If you’re interested in the concept then you can read more about it in the paper published by the researchers.