VideoFlow: A Conditional Flow-Based Model for Stochastic Video Generation

Generative models that can model and predict sequences of future events can, in principle, learn to capture complex real-world phenomena, such as physical interactions. However, a central challenge in video prediction is that the future is highly uncertain: a sequence of past observations of events can imply many possible futures. Although a number of recent works have studied probabilistic models that can represent uncertain futures, such models are either extremely expensive computationally as in the case of pixel-level autoregressive models, or do not directly optimize the likelihood of the data. To our knowledge, our work is the first to propose multi-frame video prediction with normalizing flows, which allows for direct optimization of the data likelihood, and produces high-quality stochastic predictions. We describe an approach for modeling the latent space dynamics, and demonstrate that flow-based generative models offer a viable and competitive approach to generative modelling of video.

PDF Abstract ICLR 2020 PDF ICLR 2020 Abstract


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Video Generation BAIR Robot Pushing VideoFlow FVD score 131±5 # 15
Cond 3 # 30
Pred 14 (total 16) # 2
Train 10 # 23


No methods listed for this paper. Add relevant methods here