Abstract
Predicting future frames for a video sequence is a challenging generative modeling task. Promising approaches include probabilistic latent variable models such as the Variational Auto-Encoder. While VAEs can handle uncertainty and model multiple possible future outcomes, they have a tendency to produce blurry predictions. In this work we argue that this is a sign of underfitting. To address this issue, we propose to increase the expressiveness of the latent distributions and to use higher capacity likelihood models. Our approach relies on a hierarchy of latent variables, which defines a family of flexible prior and posterior distributions in order to better model the probability of future sequences. We validate our proposal through a series of ablation experiments and compare our approach to current state-of-the-art latent variable models. Our method performs favorably under several metrics in three different datasets.
Abstract (translated)
预测视频序列的未来帧是一项具有挑战性的生成建模任务。有希望的方法包括概率潜在变量模型，如变分自动编码器。虽然Vaes可以处理不确定性并对多种可能的未来结果进行建模，但它们有产生模糊预测的倾向。在这项工作中，我们认为这是一个不足的迹象。为了解决这个问题，我们建议增加潜在分布的表现力，并使用更高容量的似然模型。我们的方法依赖于潜在变量的层次结构，它定义了一系列灵活的前后分布，以便更好地建模未来序列的概率。我们通过一系列烧蚀实验验证了我们的建议，并将我们的方法与当前最先进的潜在变量模型进行了比较。我们的方法在三个不同数据集中的多个度量下表现良好。
URL
https://arxiv.org/abs/1904.12165
