Metraipolis › archive › dc_6801a7d3dbd2

A Variational Optimal Transport Operator on Incompressible Flow — arXiv:2609.13729

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.13729
License (as archived)
CC0-1.0
Archived
2026-10-16T00:10:28.529Z
SHA-256 of the archived text
193d8bca9b8d5831e4962f64465c05fc4a3c142754b73ad1ec7d8c6b9bb60ab3
Stable URL of this page
https://metraipolis.com/documento/dc_6801a7d3dbd2

How to cite

A Variational Optimal Transport Operator on Incompressible Flow — arXiv:2609.13729 — arXiv (en), https://arxiv.org/abs/2609.13729 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6801a7d3dbd2 (Metraipolis archive dc_6801a7d3dbd2, sha256 193d8bca9b8d5831e4962f64465c05fc4a3c142754b73ad1ec7d8c6b9bb60ab3)
BibTeX
@misc{dc6801a7d3dbd2,
  title = {A Variational Optimal Transport Operator on Incompressible Flow — arXiv:2609.13729},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.13729},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6801a7d3dbd2; sha256 193d8bca9b8d5831e4962f64465c05fc4a3c142754b73ad1ec7d8c6b9bb60ab3},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.13729. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We present the Variational Incompressible Optimal Transport (VIOT) operator, a generative neural operator for amortized incompressible density transport. Given a new source-target density pair, VIOT predicts a divergence-free velocity field and generates the full transport trajectory by feed-forward inference, replacing the hour-scale per-pair optimization used by adjoint fluid solvers and differentiable simulation baselines. The system consists of three components: a stream-function or vector-potential representation that enforces incompressibility by construction, a regularized incompressible transport objective that balances endpoint accuracy and flow smoothness, and a Fourier Neural Operator backbone that amortizes the solve across new pairs and grid resolutions. Together, these components make incompressible transport a reusable neural operator that facilitates various transport processes. Further, the generative capability extends beyond the training distribution, with VIOT producing incompressible transports for user-drawn source-target pairs in a real-time interactive system. We demonstrate VIOT on 2D and 3D density-transport benchmarks. Both 2D and 3D rollouts complete in seconds per pair, while per-instance baselines in our 2D comparisons optimize each new pair from scratch and require on the order of an hour, a roughly $10^4\times$ online speedup.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-15 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG) ; Graphics (cs.GR).
Pagina del lavoro: https://arxiv.org/abs/2609.13729 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-15T23:54:14.634Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).