1 code implementation • 6 Oct 2021 • Hafez Farazi, Jan Nogga, and Sven Behnke
The ultimate goal of video prediction is not forecasting future pixel-values given some previous frames.
1 code implementation • 10 May 2021 • Hafez Farazi, Jan Nogga, Sven Behnke
Although these models can predict the future frames, they rely entirely on these recurrent structures to simultaneously perform three distinct tasks: extracting transformations, projecting them into the future, and transforming the current frame.