# Efficient training for future video generation based on hierarchical disentangled representation of latent variables

arXiv: https://arxiv.org/abs/2106.03502 · HTML: https://mlsanity.com/paper/2106.03502/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 31 references that are in the map.
- First posted on arXiv 7 Jun 2021.

## Builds on (most cited first, 26 of 26)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [Spatial Transformer Networks](https://mlsanity.com/paper/1506.02025/) (2015)
- [Which Training Methods for GANs do actually Converge?](https://mlsanity.com/paper/1801.04406/) (2018)
- [MoCoGAN: Decomposing Motion and Content for Video Generation](https://mlsanity.com/paper/1707.04993/) (2017)
- [Generating Videos with Scene Dynamics](https://mlsanity.com/paper/1609.02612/) (2016)
- [Dynamic Filter Networks](https://mlsanity.com/paper/1605.09673/) (2016)
- [An Intriguing Failing of Convolutional Neural Networks and the CoordConv Solution](https://mlsanity.com/paper/1807.03247/) (2018)
- [Deep multi-scale video prediction beyond mean square error](https://mlsanity.com/paper/1511.05440/) (2015)
- [Unsupervised Learning for Physical Interaction through Video Prediction](https://mlsanity.com/paper/1605.07157/) (2016)
- [Attend, Infer, Repeat: Fast Scene Understanding with Generative Models](https://mlsanity.com/paper/1603.08575/) (2016)
- [Temporal Generative Adversarial Nets with Singular Value Clipping](https://mlsanity.com/paper/1611.06624/) (2016)
- [Decomposing Motion and Content for Natural Video Sequence Prediction](https://mlsanity.com/paper/1706.08033/) (2017)
- [Unsupervised Learning of Disentangled Representations from Video](https://mlsanity.com/paper/1705.10915/) (2017)
- [Learning to Decompose and Disentangle Representations for Video Prediction](https://mlsanity.com/paper/1806.04166/) (2018)
- [Train Sparsely, Generate Densely: Memory-efficient Unsupervised Training of High-resolution Temporal GAN](https://mlsanity.com/paper/1811.09245/) (2018)
- [Spatial Broadcast Decoder: A Simple Architecture for Learning Disentangled Representations in VAEs](https://mlsanity.com/paper/1901.07017/) (2019)
- [Learning to Generate Long-term Future via Hierarchical Prediction](https://mlsanity.com/paper/1704.05831/) (2017)
- [The Pose Knows: Video Forecasting by Generating Pose Futures](https://mlsanity.com/paper/1705.00053/) (2017)
- [Deep Video Generation, Prediction and Completion of Human Action Sequences](https://mlsanity.com/paper/1711.08682/) (2017)
- [Adversarial Video Generation on Complex Datasets](https://mlsanity.com/paper/1907.06571/) (2019)
- [Transformation-Based Models of Video Sequences](https://mlsanity.com/paper/1701.08435/) (2017)
- [Hierarchical Video Generation from Orthogonal Information: Optical Flow and Texture](https://mlsanity.com/paper/1711.09618/) (2017)
- [Long-Term Human Video Generation of Multiple Futures Using Poses](https://mlsanity.com/paper/1904.07538/) (2019)

## Abstract (arXiv)

Generating videos predicting the future of a given sequence has been an area of active research in recent years. However, an essential problem remains unsolved: most of the methods require large computational cost and memory usage for training. In this paper, we propose a novel method for generating future prediction videos with less memory usage than the conventional methods. This is a critical stepping stone in the path towards generating videos with high image quality, similar to that of generated images in the latest works in the field of image generation. We achieve high-efficiency by training our method in two stages: (1) image reconstruction to encode video frames into latent variables, and (2) latent variable prediction to generate the future sequence. Our method achieves an efficient compression of video into low-dimensional latent variables by decomposing each frame according to its hierarchical structure. That is, we consider that video can be separated into background and foreground objects, and that each object holds time-varying and time-independent information independently. Our experiments show that the proposed method can efficiently generate future prediction videos, even for complex datasets that cannot be handled by previous methods.