arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1903.01434cs.CVcs.AIcs.LG
收藏

VideoFlow:一种基于条件流的随机视频生成模型

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

Google Research, Brain Team(谷歌研究院大脑团队)

Manoj Kumar, Mohammad Babaeizadeh, Dumitru Erhan, Chelsea Finn, Sergey Levine, Laurent Dinh, Durk Kingma

摘要:

原则上,可以建模和预测未来事件序列的生成模型可以学习捕获复杂的现实世界现象,例如物理交互。然而,视频预测的一个核心挑战是未来是高度不确定的:过去对事件的一系列观察可能意味着许多可能的未来。虽然最近的一些作品已经研究了概率模型,可以代表不确定的未来,这样的模型要么是非常昂贵的计算像素级自回归模型的情况下,或不直接优化数据的可能性。据我们所知,我们的工作是第一个提出多帧视频预测与规范化流,它允许直接优化的数据可能性,并产生高质量的随机预测。我们描述了一种建模的潜在空间动态的方法,并证明了基于流的生成模型提供了一个可行的和有竞争力的方法生成建模的视频。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑