Learning in-between imagery dynamics via physical latent spaces

DOI10.1137/23M1609440MaRDI QIDQ6623698zbMATH OpenFDO

Authors Jihun Han, Yoonsang Lee, Anne Gelb

Publication date 24 October 2024

Published in SIAM Journal on Scientific Computing (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1137/23M1609440

zbMATH Keywords

in-between image dynamicsinterpretabilityphysical latent space

Mathematics Subject Classification ID

Simulation of dynamical systems (37M05) Machine vision and scene understanding (68T45)

Recommendations

• Physical representation learning and parameter identification from video using differentiable physics
• Interpretable model learning in variational imaging: a bilevel optimization approach
• Discovering phase field models from image data with the pseudo-spectral physics informed neural networks
• Physics-informed semantic inpainting: application to geostatistical modeling

Cites work

• Data-driven identification of parametric partial differential equations
• Deep learning for physical processes: incorporating prior scientific knowledge
• Efficient and exact multimarginal optimal transport with pairwise costs
• Optimal Transport
• Optimal transport for particle image velocimetry
• Optimal transport for particle image velocimetry: real data and postprocessing algorithms
• The existence of minimizers for an isoperimetric problem with Wasserstein penalty term in unbounded domains

Cited in

(1)

• Deep variational Luenberger-type observer with dynamic objects channel-attention for stochastic video prediction

This page was built for publication: Learning in-between imagery dynamics via physical latent spaces

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6623698)