# PDE-Driven Spatiotemporal Disentanglement

arXiv: https://arxiv.org/abs/2008.01352 · HTML: https://mlsanity.com/paper/2008.01352/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Aug 2020.

## Built on by (most cited first, 19 of 19)

- [Continuous PDE Dynamics Forecasting with Implicit Neural Representations](https://mlsanity.com/paper/2209.14855/) (2022)
- [Physics-Guided Deep Learning for Dynamical Systems: A Survey](https://mlsanity.com/paper/2107.01272/) (2021)
- [Meta-Learning Dynamics Forecasting Using Task Inference](https://mlsanity.com/paper/2102.10271/) (2021)
- [Continuous Field Reconstruction from Sparse Observations with Implicit Neural Networks](https://mlsanity.com/paper/2401.11611/) (2024)
- [Earthfarseer: Versatile Spatio-Temporal Dynamical Systems Modeling in One Model](https://mlsanity.com/paper/2312.08403/) (2023)
- [Learning Robust Dynamics through Variational Sparse Gating](https://mlsanity.com/paper/2210.11698/) (2022)
- [Disentangling Generative Factors of Physical Fields Using Variational Autoencoders](https://mlsanity.com/paper/2109.07399/) (2021)
- [CMS-LSTM: Context Embedding and Multi-Scale Spatiotemporal Expression LSTM for Predictive Learning](https://mlsanity.com/paper/2102.03586/) (2021)
- [Gaussian Process Latent Variable Modeling for Few-shot Time Series Forecasting](https://mlsanity.com/paper/2212.10306/) (2022)
- [MoDeRNN: Towards Fine-grained Motion Details for Spatiotemporal Predictive Learning](https://mlsanity.com/paper/2110.12978/) (2021)
- [TaylorSwiftNet: Taylor Driven Temporal Modeling for Swift Future Frame Prediction](https://mlsanity.com/paper/2110.14392/) (2021)
- [STONet: A Neural-Operator-Driven Spatio-temporal Network](https://mlsanity.com/paper/2204.08414/) (2022)
- [Guiding Video Prediction with Explicit Procedural Knowledge](https://mlsanity.com/paper/2406.18220/) (2024)
- [Breaking Scale Anchoring: Frequency Representation Learning for Accurate High-Resolution Inference from Low-Resolution Training](https://mlsanity.com/paper/2512.05132/) (2025)
- [Taylor saves for later: disentanglement for video prediction using Taylor representation](https://mlsanity.com/paper/2105.11062/) (2021)
- [Inference-InfoGAN: Inference Independence via Embedding Orthogonal Basis Expansion](https://mlsanity.com/paper/2110.00788/) (2021)
- [ViPro: Enabling and Controlling Video Prediction for Complex Dynamical Scenarios using Procedural Knowledge](https://mlsanity.com/paper/2407.09537/) (2024)
- [ViPro-2: Unsupervised State Estimation via Integrated Dynamics for Guiding Video Prediction](https://mlsanity.com/paper/2508.06335/) (2025)
- [Sequence-Adaptive Video Prediction in Continuous Streams using Diffusion Noise Optimization](https://mlsanity.com/paper/2511.18255/) (2025)

## Abstract (arXiv)

A recent line of work in the machine learning community addresses the problem of predicting high-dimensional spatiotemporal phenomena by leveraging specific tools from the differential equations theory. Following this direction, we propose in this article a novel and general paradigm for this task based on a resolution method for partial differential equations: the separation of variables. This inspiration allows us to introduce a dynamical interpretation of spatiotemporal disentanglement. It induces a principled model based on learning disentangled spatial and temporal representations of a phenomenon to accurately predict future observations. We experimentally demonstrate the performance and broad applicability of our method against prior state-of-the-art models on physical and synthetic video datasets.