Metraipolis › archive › dc_770444786490
Lagrangian--Hamiltonian Flows for Video Prediction and Image Generation: A Symplectic Perspective — arXiv:2609.35710
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.35710
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T23:54:57.550Z
- SHA-256 of the archived text
3daaccf7761c7919482b9f435c5b9a3a6e99483df8b8b9b17b0d93faaf5af73b- Stable URL of this page
https://metraipolis.com/documento/dc_770444786490
How to cite
Lagrangian--Hamiltonian Flows for Video Prediction and Image Generation: A Symplectic Perspective — arXiv:2609.35710 — arXiv (en), https://arxiv.org/abs/2609.35710 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_770444786490 (Metraipolis archive dc_770444786490, sha256 3daaccf7761c7919482b9f435c5b9a3a6e99483df8b8b9b17b0d93faaf5af73b)
BibTeX
@misc{dc770444786490,
title = {Lagrangian--Hamiltonian Flows for Video Prediction and Image Generation: A Symplectic Perspective — arXiv:2609.35710},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.35710},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_770444786490; sha256 3daaccf7761c7919482b9f435c5b9a3a6e99483df8b8b9b17b0d93faaf5af73b},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.35710. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We introduce LHFM, a geometric framework for learning image dynamics. Drawing on structures central to classical mechanics, symplectic geometry, and geometric quantization, LHFM represents each image as an exact Lagrangian graph and models its evolution through image-dependent Hamiltonian flows, which yield a transport--source parameterization of image velocities. Our primary application is deterministic video prediction: LHFM-V is a recurrent model that advances frames by integrating predicted transport and source fields, and achieves the lowest reported FLOP count among the compared recurrent models with similar prediction accuracy. The image variant, LHFM-I, shows that the same construction is compatible with flow matching: in a matched experiment, it attains a lower FID than the flow-matching baseline. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-29 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.35710 — 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 2026-10-07T23:29:27.623Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).