VideoFlow: A Conditional Flow-Based Model for Stochastic Video Generation
Preprint
Abstract
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.Keywords
All Related Versions
This publication has 7 references indexed in Scilit:
- Learning Dynamic Generator Model by Alternating Back-Propagation through TimeProceedings of the AAAI Conference on Artificial Intelligence, 2019
- Waveglow: A Flow-based Generative Network for Speech Synthesis2019
- Cooperative Training of Descriptor and Generator NetworksIEEE Transactions on Pattern Analysis and Machine Intelligence, 2018
- Mastering the game of Go without human knowledgeNature, 2017
- Deep Residual Learning for Image Recognition2016
- Human3.6M: Large Scale Datasets and Predictive Methods for 3D Human Sensing in Natural EnvironmentsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2013
- Image quality assessment: from error visibility to structural similarityIEEE Transactions on Image Processing, 2004