AI-Based Video-to-Video Synthesis – Two minutes papers

Two Minute Papers – AI-Based Video-to-Video Synthesis



Research at NVIDIA: Video to Video Synthesis



The paper “Video-to-Video Synthesis” and its source code is available here:



  • Label-to-Streetview Results


  • Edge-to-Face Results


  • Pose-to-Body Results

Leave a Reply

This site uses Akismet to reduce spam. Learn how your comment data is processed.

%d bloggers like this: