Image and Video Synthesis: How, Why and "What if"?

ICCV 2019 Workshop

Seoul, Korea

Monday, October 28, 2019

Room E5, E6

Generative modeling approaches are now at the point where high definition images can be synthesized from noise vectors and conditional methods enable video synthesis and future prediction. These technologies are reaching the point when they work well enough to both fascinate and disturb the general public, and to provide a rich unexplored medium of expression for artists.

While the end results seem similar, the approaches taken in visual synthesis range from conditional generative adversarial networks, through variational auto encoders to traditional graphics tricks of the trade. Moreover, the goals of synthesis research vary from modeling statistical distributions in machine learning, through realistic picture-perfect recreations of the world in graphics, and all the way to providing tools of artistic expression.

Additionally, there is a disconnect between research aimed at synthesis and practitioners interested in forensics. The issue of fake content synthesis and detection has recently become relevant to the public at large as a result of current political and social trends, and we can no longer afford to operate in two parallel universes.


  1. To bring together experts from multiple disciplines working on and with synthesis to learn from each other.
  2. To encourage discussion on the underlying goals of video and image synthesis, the ethics surrounding the resulting artifacts and the need for forensics to separate the fake from the real.


Submissions to win an NVIDIA GPU are now closed.

See the Gallery for submitted works.


The program will consist of invited talks from research leaders and leading digital artist on the topics of synthesis and forensics, followed by a panel discussion on ethics and societal issues in synthesis algorithms. Speakers are encouraged to discuss ethical issues in their talks.






8:45 - 9:00

Opening remarks

9:00 - 9:30

University of Michigan

9:30 - 10:00

Aalto University and NVIDIA

10:00 - 11:00

Coffee Break

11:30 - 12:00


The Structure and Interpretation of a GAN

12:00 - 13:30


13:30 - 14:00

UC Berkeley

14:00 - 14:30

The University of Chicago

14:30 - 15:00

University of Washington

15:00 - 15:30

Technical University Munich

AI-Driven Videos Synthesis and its Implications

15:30 - 16:30

Coffee Break

16:30 - 17:00



Panel of speakers with special guest, Professor Jitendra Malik, and discussion led by Alyosha Efros.

Possible topics:

  • Should there be ethical guidelines for image manipulation research?
  • Why isn’t there enough forensics research? How do we get people excited about it?
  • Is the bottleneck problem in forensics really a user interface problem?
  • Are image and video synthesis models overrated? What is the purpose of this work?
  • There are many accusatory comments against big corporations and government agencies for not preventing or dealing with fake imagery. Are there meaningful government regulations that should be applied to fake imagery? Are there corporate regulations/solutions that can be enforced and applied? Is the real problem an “ethics” one or a public policy one?
  • As a discipline, how do we move past the hand-waving or even fear-mongering discussion of ethics to something more tangible? What are the concrete, actionable questions or even grand challenge-style problems that we should engage in answering?


Awards Ceremony



This workshop was generously sponsored by Adobe and NVIDIA.