Metraipolis › archive › dc_cd551a2a009b

WorldCrafter: Consistent Video World Model with Implicit 3D-aware Memory — arXiv:2609.24984

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.24984
License (as archived)
CC0-1.0
Archived
2026-10-09T22:06:28.519Z
SHA-256 of the archived text
28b4f9c0b522c75931194f1ec04c877833875229b7a86c2d64ace17fa1a537a7
Stable URL of this page
https://metraipolis.com/documento/dc_cd551a2a009b

How to cite

WorldCrafter: Consistent Video World Model with Implicit 3D-aware Memory — arXiv:2609.24984 — arXiv (en), https://arxiv.org/abs/2609.24984 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cd551a2a009b (Metraipolis archive dc_cd551a2a009b, sha256 28b4f9c0b522c75931194f1ec04c877833875229b7a86c2d64ace17fa1a537a7)
BibTeX
@misc{dccd551a2a009b,
  title = {WorldCrafter: Consistent Video World Model with Implicit 3D-aware Memory — arXiv:2609.24984},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.24984},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cd551a2a009b; sha256 28b4f9c0b522c75931194f1ec04c877833875229b7a86c2d64ace17fa1a537a7},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.24984. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Video world models enable interactive exploration of dynamic environments, yet struggle to respect prior observations over long horizons and across viewpoints. We present WorldCrafter, a video world model that learns a camera-queryable implicit 3D-aware memory for this purpose. The key insight is to let the requested viewpoint shape how multi-view evidence is compressed into the video generator's limited token budget. Trained jointly with the video generator, a memory encoder and pose-conditioned readout module integrate historical observations into a fixed set of target view-specific tokens before denoising, without explicit depth-based correspondences. By combining this memory with recent temporal context and few-step distillation, WorldCrafter enables streaming scene exploration from a single input image or text prompt. Experiments across static and dynamic scenes show substantial gains in long-horizon consistency and camera-control accuracy while preserving visual quality during minute-scale exploration.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-22 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI); Graphics (cs.GR).
Pagina del lavoro: https://arxiv.org/abs/2609.24984 — 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 2026-10-09T21:45:21.109Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).