Google DeepMind’s Transframer Generates 30-Second Videos from Single Image Frames

Google’s DeepMind network can create short videos using a single frame of an image. It’s amazing.

Transframer is an all-purpose generative framework capable of handling many image and video tasks within a probabilistic environment. New work shows it excels in video prediction and view synthesis, and can generate 30s videos from a single image: 1/\”


Leave a Reply

Your email address will not be published. Required fields are marked *