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: https://tcwang0509.github.io/vid2vid/

https://github.com/NVIDIA/vid2vid

 

 

  • 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.