Hacker News new | past | comments | ask | show | jobs | submit login
Generating Videos with Scene Dynamics (web.mit.edu)
1 point by RyanMcGreal on Dec 9, 2016 | hide | past | favorite | 1 comment



From the technical overview:

Our approach builds on generative image models that leverage adversarial learning, which we apply to video. The basic idea behind the approach is to compete two deep networks against each other. One network ("the generator") tries to generate a synthetic video, and another network ("the discriminator") tries to discriminate synthetic versus real videos. The generator is trained to fool the discriminator.




Join us for AI Startup School this June 16-17 in San Francisco!

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: