Self-supervised inpainting with local neighbourhood tokenisation learns reusable priors for 3D fluid velocity fields that outperform supervised neural surrogates under boundary-condition and dataset shifts on intracranial aneurysm data.
Holzschuh and Qiang Liu and Georg Kohl and Nils Thuerey , editor =
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Inpainting physics: self-supervised learning for context-driven fluid simulation
Self-supervised inpainting with local neighbourhood tokenisation learns reusable priors for 3D fluid velocity fields that outperform supervised neural surrogates under boundary-condition and dataset shifts on intracranial aneurysm data.