# Learning to Decompose and Disentangle Representations for Video Prediction

arXiv: https://arxiv.org/abs/1806.04166 · HTML: https://mlsanity.com/paper/1806.04166/

## Key facts

- Cited by 121 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Jun 2018.

## Built on by (most cited first, 30 of 121)

- [DriveDreamer: Towards Real-world-driven World Models for Autonomous Driving](https://mlsanity.com/paper/2309.09777/) (2023)
- [DriveDreamer-2: LLM-Enhanced World Models for Diverse Driving Video Generation](https://mlsanity.com/paper/2403.06845/) (2024)
- [Generating Videos with Dynamics-aware Implicit Generative Adversarial Networks](https://mlsanity.com/paper/2202.10571/) (2022)
- [SimVP: Simpler yet Better Video Prediction](https://mlsanity.com/paper/2206.05099/) (2022)
- [PredRNN: A Recurrent Neural Network for Spatiotemporal Predictive Learning](https://mlsanity.com/paper/2103.09504/) (2021)
- [A Good Image Generator Is What You Need for High-Resolution Video Synthesis](https://mlsanity.com/paper/2104.15069/) (2021)
- [Deep Stable Learning for Out-Of-Distribution Generalization](https://mlsanity.com/paper/2104.07876/) (2021)
- [DriveGAN: Towards a Controllable High-Quality Neural Simulation](https://mlsanity.com/paper/2104.15060/) (2021)
- [Disentangled Representation Learning](https://mlsanity.com/paper/2211.11695/) (2022)
- [Temporal Attention Unit: Towards Efficient Spatiotemporal Predictive Learning](https://mlsanity.com/paper/2206.12126/) (2022)
- [InfiniteNature-Zero: Learning Perpetual View Generation of Natural Scenes from Single Images](https://mlsanity.com/paper/2207.11148/) (2022)
- [OOD-GNN: Out-of-Distribution Generalized Graph Neural Network](https://mlsanity.com/paper/2112.03806/) (2021)
- [E-NeRV: Expedite Neural Video Representation with Disentangled Spatial-Temporal Context](https://mlsanity.com/paper/2207.08132/) (2022)
- [Greedy Hierarchical Variational Autoencoders for Large-Scale Video Prediction](https://mlsanity.com/paper/2103.04174/) (2021)
- [Cloth-Changing Person Re-identification from A Single Image with Gait Prediction and Regularization](https://mlsanity.com/paper/2103.15537/) (2021)
- [Learning Multi-Object Dynamics with Compositional Neural Radiance Fields](https://mlsanity.com/paper/2202.11855/) (2022)
- [Video Prediction Recalling Long-term Motion Context via Memory Alignment Learning](https://mlsanity.com/paper/2104.00924/) (2021)
- [Unsupervised Semantic Segmentation with Self-supervised Object-centric Representations](https://mlsanity.com/paper/2207.05027/) (2022)
- [OpenSTL: A Comprehensive Benchmark of Spatio-Temporal Predictive Learning](https://mlsanity.com/paper/2306.11249/) (2023)
- [Iso-Dream: Isolating and Leveraging Noncontrollable Visual Dynamics in World Models](https://mlsanity.com/paper/2205.13817/) (2022)
- [Self-Supervised Learning Disentangled Group Representation as Feature](https://mlsanity.com/paper/2110.15255/) (2021)
- [Persistent Nature: A Generative Model of Unbounded 3D Worlds](https://mlsanity.com/paper/2303.13515/) (2023)
- [Efficient Video Diffusion Models via Content-Frame Motion-Latent Decomposition](https://mlsanity.com/paper/2403.14148/) (2024)
- [A Novel Estimator of Mutual Information for Learning to Disentangle Textual Representations](https://mlsanity.com/paper/2105.02685/) (2021)
- [Learning Object-Centric Representations of Multi-Object Scenes from Multiple Views](https://mlsanity.com/paper/2111.07117/) (2021)
- [Show Me What and Tell Me How: Video Synthesis via Multimodal Conditioning](https://mlsanity.com/paper/2203.02573/) (2022)
- [Video Autoencoder: self-supervised disentanglement of static 3D structure and motion](https://mlsanity.com/paper/2110.02951/) (2021)
- [Tell Me What Happened: Unifying Text-guided Video Completion via Multimodal Masked Video Generation](https://mlsanity.com/paper/2211.12824/) (2022)
- [UniMLVG: Unified Framework for Multi-view Long Video Generation with Comprehensive Control Capabilities for Autonomous Driving](https://mlsanity.com/paper/2412.04842/) (2024)
- [OGC: Unsupervised 3D Object Segmentation from Rigid Dynamics of Point Clouds](https://mlsanity.com/paper/2210.04458/) (2022)

## Abstract (arXiv)

Our goal is to predict future video frames given a sequence of input frames. Despite large amounts of video data, this remains a challenging task because of the high-dimensionality of video frames. We address this challenge by proposing the Decompositional Disentangled Predictive Auto-Encoder (DDPAE), a framework that combines structured probabilistic models and deep networks to automatically (i) decompose the high-dimensional video that we aim to predict into components, and (ii) disentangle each component to have low-dimensional temporal dynamics that are easier to predict. Crucially, with an appropriately specified generative model of video frames, our DDPAE is able to learn both the latent decomposition and disentanglement without explicit supervision. For the Moving MNIST dataset, we show that DDPAE is able to recover the underlying components (individual digits) and disentanglement (appearance and location) as we would intuitively do. We further demonstrate that DDPAE can be applied to the Bouncing Balls dataset involving complex interactions between multiple objects to predict the video frame directly from the pixels and recover physical states without explicit supervision.