7 votes

Few-shot Video-to-Video Synthesis

2 comments

  1. balooga
    Link
    This is astonishing technology. The next 20 years are going to be a lot weirder than I ever expected.

    This is astonishing technology. The next 20 years are going to be a lot weirder than I ever expected.

    2 votes
  2. skybrian
    Link
    From the abstract:

    From the abstract:

    [W]e propose a few-shot vid2vid framework, which learns to synthesize videos of previously unseen subjects or scenes by leveraging few example images of the target at test time. Our model achieves this few-shot generalization capability via a novel network weight generation module utilizing an attention mechanism. We conduct extensive experimental validations with comparisons to strong baselines using several large-scale video datasets including human-dancing videos, talking-head videos, and street-scene videos.

    1 vote