Stochastic Adversarial Video Prediction
Being able to predict what may happen in the future requires an in-depth understanding of the physical and causal rules that govern the world. A model that is able to do so has a number of appealing applications, from robotic planning to representation learning. However, learning to predict raw futu...
Gespeichert in:
Hauptverfasser: | , , , , , |
---|---|
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | Being able to predict what may happen in the future requires an in-depth
understanding of the physical and causal rules that govern the world. A model
that is able to do so has a number of appealing applications, from robotic
planning to representation learning. However, learning to predict raw future
observations, such as frames in a video, is exceedingly challenging -- the
ambiguous nature of the problem can cause a naively designed model to average
together possible futures into a single, blurry prediction. Recently, this has
been addressed by two distinct approaches: (a) latent variational variable
models that explicitly model underlying stochasticity and (b)
adversarially-trained models that aim to produce naturalistic images. However,
a standard latent variable model can struggle to produce realistic results, and
a standard adversarially-trained model underutilizes latent variables and fails
to produce diverse predictions. We show that these distinct methods are in fact
complementary. Combining the two produces predictions that look more realistic
to human raters and better cover the range of possible futures. Our method
outperforms prior and concurrent work in these aspects. |
---|---|
DOI: | 10.48550/arxiv.1804.01523 |