Metraipolis › archive › dc_20278ff29caa

MotionCraft: Latent World Modeling with Sparse Attention for Visual Upscaling — arXiv:2608.08553

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.08553
License (as archived)
CC0-1.0
Archived
2026-10-19T09:15:42.513Z
SHA-256 of the archived text
0286e72ceee0cf90d882034dcc21fcca7a0d0242d4e38cd1b4caef7f8a95415b
Stable URL of this page
https://metraipolis.com/documento/dc_20278ff29caa

How to cite

MotionCraft: Latent World Modeling with Sparse Attention for Visual Upscaling — arXiv:2608.08553 — arXiv (en), https://arxiv.org/abs/2608.08553 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_20278ff29caa (Metraipolis archive dc_20278ff29caa, sha256 0286e72ceee0cf90d882034dcc21fcca7a0d0242d4e38cd1b4caef7f8a95415b)
BibTeX
@misc{dc20278ff29caa,
  title = {MotionCraft: Latent World Modeling with Sparse Attention for Visual Upscaling — arXiv:2608.08553},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.08553},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_20278ff29caa; sha256 0286e72ceee0cf90d882034dcc21fcca7a0d0242d4e38cd1b4caef7f8a95415b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.08553. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Video super-resolution (VSR) aims to recover high-fidelity high-resolution videos from low-resolution inputs and is central to applications ranging from mobile capture to streaming and archival restoration. Existing approaches trade off among local-detail fidelity, long-range spatio-temporal modeling, perceptual realism, and efficiency: convolutional alignment techniques preserve local structure but suffer when motion is large or degradations are complex; transformer-based methods capture long-range dependencies yet require architectural or algorithmic adaptations to remain computationally feasible; and recent latent or diffusion-based generators synthesize rich texture but require specialized temporal constraints to maintain coherence. We present MotionCraft, a controllable VSR framework that formulates restoration as motion-aware latent state prediction inspired by world models and integrates adaptive sparse attention with an explicit user-accessible control interface. MotionCraft combines robust motion fusion, a Latent World Transformer that balances locality and targeted non-local interactions, and a compact conditional decoder to deliver temporally consistent, high-quality reconstructions under streaming constraints. Empirical evaluations show that MotionCraft achieves strong reconstruction and perceptual performance while enabling predictable trade-offs between temporal smoothness and reconstruction fidelity.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-11 in cs.MM).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Machine Learning (cs.LG); Multimedia (cs.MM).
Pagina del lavoro: https://arxiv.org/abs/2608.08553 — 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 2026-10-19T09:13:27.080Z dalla pagina https://arxiv.org/catchup/cs.MM/2026-08-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).