Scientists have developed an artificial intelligence (AI) system that can sketch caricatures from a given portrait.
Caricature portrait drawing is a distinct art form where artists draw a person’s face in an exaggerated manner, most times to elicit humour. Automating this technique poses challenges due to the amount of intricate details and shapes involved and level of professional skills it takes to transform a person artistically from their real-life selves to a creatively exaggerated one.
“Compared to traditional graphics-based methods which define hand-crafted rules, our novel approach leverages big data and machine learning to synthesize caricatures from thousands of examples drawn by professional artists,” said Kaidi Cao, a graduate student at Stanford University in the US.
“While existing style transfer methods have focused mainly on appearance style, our technique achieves both geometric exaggeration and appearance stylisation involved in caricature drawing,” said Cao, who conducted the work during his internship at Microsoft. The method enables the users to automate caricatures of portraits, and can be applied to tasks such as creating caricatured avatars for social media, and designing cartoon characters.
This technique also has certain potential applications in marketing, advertising and also in the field of journalism.
The researchers turned to a well-known technique in machine learning, Generative Adversarial Network (GAN), for unpaired photo-to-caricature translation to generate caricatures that preserve the identity of the portrait. (PTI)
