Metraipolis › archive › dc_c0a2b01a02c8

MotionCore: A Latent Neural Simulator for Video Generation with Rigid-Body Dynamics — arXiv:2611.08904

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.08904
License (as archived)
CC0-1.0
Archived
2026-11-09T22:45:09.436Z
SHA-256 of the archived text
74898eb99ac490e8f19be44364c01bee0857237fde012a4b8e7dc826a35a5808
Stable URL of this page
https://metraipolis.com/documento/dc_c0a2b01a02c8

How to cite

MotionCore: A Latent Neural Simulator for Video Generation with Rigid-Body Dynamics — arXiv:2611.08904 — arXiv (en), https://arxiv.org/abs/2611.08904 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c0a2b01a02c8 (Metraipolis archive dc_c0a2b01a02c8, sha256 74898eb99ac490e8f19be44364c01bee0857237fde012a4b8e7dc826a35a5808)
BibTeX
@misc{dcc0a2b01a02c8,
  title = {MotionCore: A Latent Neural Simulator for Video Generation with Rigid-Body Dynamics — arXiv:2611.08904},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.08904},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c0a2b01a02c8; sha256 74898eb99ac490e8f19be44364c01bee0857237fde012a4b8e7dc826a35a5808},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.08904. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Video generation models can produce highly realistic videos while generating physically inconsistent object motion. This limitation suggests that visual modeling alone may not provide a transferable representation of physical dynamics. We introduce MotionCore, a framework for learning physical dynamics via a learnable partial differential equation solver and focuses on rigid-body motion. We introduce a latent neural simulator learning to predict the evolution of object-level physical states from observed motion. Its predictions are then converted into spatially aligned latent controls for a controllable video diffusion model. The generator serves as a visual interface: it provides appearance and scene detail, while the learned dynamics model specifies the physical trajectory. To preserve this trajectory through the interface, MotionCore combines a diffusion-matching objective with a low-capacity decodability constraint on object identity and position. We evaluate MotionCore on public physical-consistency benchmarks and on paired data with known trajectories. Results indicate that MotionCore improves physical consistency and trajectory obedience in the evaluated rigid-body settings, while maintaining comparable visual quality. A controlled ablation protocol compares learned dynamics with an analytic prior and studies the choice of latent evolution processor.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2611.08904 — 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 2026-11-09T22:37:47.210Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).