Filtered-CoPhy: Unsupervised Learning of Counterfactual Physics in Pixel Space - Archive ouverte HAL Access content directly
Conference Papers Year :

Filtered-CoPhy: Unsupervised Learning of Counterfactual Physics in Pixel Space

Fabien Baradel
  • Function : Author
  • PersonId : 1131651
Natalia Neverova
  • Function : Author
  • PersonId : 1131652
Greg Mori
  • Function : Author
  • PersonId : 1033994

Abstract

Learning causal relationships in high-dimensional data (images, videos) is a hard task, as they are often defined on low-dimensional manifolds and must be extracted from complex signals dominated by appearance, lighting, textures and also spurious correlations in the data. We present a method for learning counterfactual reasoning of physical processes in pixel space, which requires the prediction of the impact of interventions on initial conditions. Going beyond the identification of structural relationships, we deal with the challenging problem of forecasting raw video over long horizons. Our method does not require the knowledge or supervision of any ground truth positions or other object or scene properties. Our model learns and acts on a suitable hybrid latent representation based on a combination of dense features, sets of 2D keypoints and an additional latent vector per keypoint. We show that this better captures the dynamics of physical processes than purely dense or sparse representations. We introduce a new challenging and carefully designed counterfactual benchmark for predictions in pixel space and outperform strong baselines in physics-inspired ML and video prediction.
Fichier principal
Vignette du fichier
CoPhy_ICLR.pdf (22.39 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03630595 , version 1 (05-04-2022)

Identifiers

  • HAL Id : hal-03630595 , version 1

Cite

Steeven Janny, Fabien Baradel, Natalia Neverova, Madiha Nadri, Greg Mori, et al.. Filtered-CoPhy: Unsupervised Learning of Counterfactual Physics in Pixel Space. International Conference on Learning Representations, Apr 2022, Virtuel, United States. ⟨hal-03630595⟩
120 View
10 Download

Share

Gmail Facebook Twitter LinkedIn More