In the month of December 2018, three researchers are expected to unveil a project that they have been working on for some time now. Stanford Graduate, Kaidi Cao, Microsoft’s Lu Yuan, and Jing Lioa from the City University of Hong Kong will unveil this project.
These researchers have created an AI based app that make use of photos of ordinary people and turn them into funny caricatures.
The AI was given training from more than a thousand different photographs and it makes use of pair network technologies known as generative adversarial networks (GANs) to generate caricatures. The first of the pair network looks at the geometry of the face to create the base model, while the second applies an artistic texture to the model to give it the hand-drawn look.
The researchers, while falling in love with the project, also claim that AI is not perfect. However, almost a quarter of the generated images can be mistaken for actual human-created caricatures.
The project has proved to be like what Microsoft revealed in the month of January 2018. That would turn photographs into what appears to be painted portraits. The main difference here is the humor and exaggeration to which the latest project submits us.
About Artificial Intelligence (AI)
Moreover, by running on Alibaba Cloud to live streams highlight reels could be generated for both matches and specific players. This AI technology is making use of both visual and audial information, which includes facial recognition, and scene detection.
AI promises new and improved possibilities for many sectors because it will drive progression from all sides as experts in the industry believe. However, there has to be significant investment in order to make AI a long term success globally.
The positive aspect in AI’s rise is the cloud computing, which is expect to help the trend to continue.
For AI to continue prospering, sectors such advertising, broadcast and media organizations must continue to incorporate it in pertinent areas.
