HOME /

meeting

Haotian Zhang, Cristobal Sciutto, Maneesh Agrawala, and Kayvon Fatahalian. 8/11/2020. “Vid2Player: Controllable Video Sprites that Behave and Appear like Professional Tennis Players.” arXiv:2008.04524 . PDFAbstract
We present a system that converts annotated broadcast video of tennis matches into interactively controllable video sprites that behave and appear like professional tennis players. Our approach is based on controllable video textures, and utilizes domain knowledge of the cyclic structure of tennis rallies to place clip transitions and accept control inputs at key decision-making moments of point play. Most importantly, we use points from the video collection to model a player's court positioning and shot selection decisions during points. We use these behavioral models to select video clips that reflect actions the real-life player is likely to take in a given match play situation, yielding sprites that behave realistically at the macro level of full points, not just individual tennis motions. Our system can generate novel points between professional tennis players that resemble Wimbledon broadcasts, enabling new experiences such as the creation of matchups between players that have not competed in real life, or interactive control of players in the Wimbledon final. According to expert tennis players, the rallies generated using our approach are significantly more realistic in terms of player behavior than video sprite methods that only consider the quality of motion transitions during video synthesis.
2020 Nov 03

Project: Pitching

12:00pm to 1:15pm

You will present 5 minute, 3-slide project pitches on Tuesday, November 3rd. 

If you are already working together, great, present together! If you'd like to find a partner, this is a good chance to see who is interested in your idea, or to hear ideas you may want to join in on. Working alone is also alright. Your slides can loosely follow this structure: 

  1. introduce your idea
  2. something about previous work you will draw on, extend, or apply
  3. some more info on a core technical challenge you anticipate
    4. ...
Read more about Project: Pitching
2020 Oct 15

Class: DeepCoder

12:00pm to 1:15pm

Eric Zhang will present the following paper and lead the discussion.

Matej Balog, Alexander L. Gaunt, Marc Brockschmidt, Sebastian Nowozin, and Daniel Tarlow. 3/8/2017. “DeepCoder: Learning to Write Programs.” arXiv:1611.01989. PDF

Pages