Wow, after reading MIT LAB on this invention, I am quite convince, we have some of deepfakes technology has already used in our world. Maybe this have removed real TV guys talking but a real person face virtually recreated.
Deepfakes
- AI-generated characters (more infamously known as ”deepfakes”) are a form of digital media generated by deep neural network.
- The real human appearance rather than animated appearance authentic to human.
- While the technology is perhaps most widely associated with media manipulation and misinformation, it is increasingly used for positive applications as well.
For Learning and Wellbeing
- AI-generated portrayals of characters can feature synthesized faces, bodies and voices of anyone.
- AI characters can be used to create learning material for all ages, from delivery of content in the classroom to engagement with content at locations like museums, historical monuments or even in nature.
- Fictional figures can be brought to life to engage learners with ‘lived’ experiences of scientists making their discoveries, historical figures narrating battles or painters discussing their inspiration and process.
- Recent leaps in generative models include generative adversarial networks (GANs).
- Since their introduction, models for AI-generated media, such as GANs, have enabled the hyper-realistic synthesis of digital content
Testing using the sample code in Colab.
Currently, generative models are being leveraged across different industries including entertainment, customer services and marketing.
Reface mobile device apps that enable users to humorously swap their faces in video clips and GIFs to share with friends.
Take care and enjoy your day.
Learn Scratch SG 