Vid2Actor: Free-viewpoint Animatable Person Synthesis from Video in the Wild
Chung-Yi Weng, Brian Curless, Ira Kemelmacher-Shlizerman
Project Page: https://grail.cs.washington.edu/projects/vid2actor/
Given an "in-the-wild" video, we train a deep network with the video frames to produce an animatable human representation that can be rendered from any camera view in any body pose, enabling applications such as motion re-targeting and bullet-time rendering without the need for rigged 3D meshes.
Photo credits:
REUTERS/Carlo Allegri
Getty Images/Clive Brunskill
Getty Images/Maddie Meyer
AP Photo/Bill Kostroun
Video links:
Novak Djokovic vs Roger Federer Full Match | US Open 2015 Final
https://youtu.be/634UMLDrVzc
US Open Tennis 2017: Roger Federer Practice
https://youtu.be/xVBb2VW6oJ4
Fik-Shun | World of Dance Las Vegas 2014
https://youtu.be/mg6-SnUl0A0
Nonstop | World of Dance Las Vegas 2015
https://youtu.be/3708rxLZyqQ