Skip to Main content Skip to Navigation
Preprints, Working Papers, ...

PDE-Driven Spatiotemporal Disentanglement

Abstract : 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.
Complete list of metadatas

Cited literature [62 references]  Display  Hide  Download
Contributor : Jean-Yves Franceschi <>
Submitted on : Monday, October 5, 2020 - 5:55:10 PM
Last modification on : Thursday, October 8, 2020 - 3:14:34 AM


Files produced by the author(s)


Distributed under a Creative Commons Attribution 4.0 International License


  • HAL Id : hal-02911067, version 2
  • ARXIV : 2008.01352


Jérémie Donà, Jean-Yves Franceschi, Sylvain Lamprier, Patrick Gallinari. PDE-Driven Spatiotemporal Disentanglement. 2020. ⟨hal-02911067v2⟩