Metraipolis › archive › dc_e57764891cdf

Complementary Retrieval-Augmented Prompting for Consistent Long-Form Video Generation — arXiv:2609.37407

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.37407
License (as archived)
CC0-1.0
Archived
2026-10-07T18:41:17.415Z
SHA-256 of the archived text
78591cc5ac296986429c4a179fcad127e4c27080850774cbad5f81034cfead8a
Stable URL of this page
https://metraipolis.com/documento/dc_e57764891cdf

How to cite

Complementary Retrieval-Augmented Prompting for Consistent Long-Form Video Generation — arXiv:2609.37407 — arXiv (en), https://arxiv.org/abs/2609.37407 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e57764891cdf (Metraipolis archive dc_e57764891cdf, sha256 78591cc5ac296986429c4a179fcad127e4c27080850774cbad5f81034cfead8a)
BibTeX
@misc{dce57764891cdf,
  title = {Complementary Retrieval-Augmented Prompting for Consistent Long-Form Video Generation — arXiv:2609.37407},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.37407},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e57764891cdf; sha256 78591cc5ac296986429c4a179fcad127e4c27080850774cbad5f81034cfead8a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.37407. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

While recent video foundation models excel at generating high-quality short videos, long-form video generation remains a critical challenge, where a major bottleneck lies in conditioning independently generated shots to preserve consistent characters, scenes, and objects throughout a story. Existing training-free approaches typically condition target shots using retrieved historical visuals. However, these references often suffer from severe informational mismatch, either introducing irrelevant contextual redundancy or failing to provide the full combination of required elements for the target shot. To resolve this, we present Complementary Retrieval-Augmented Prompting, an agentic framework that strategically aggregates a compact set of mutually supportive historical references to achieve complete and targeted conditioning for long-form video generation without retraining or modifying the underlying generator. Specifically, our framework explicitly models the visual elements required by each target shot by parsing the narrative script into a text-grounded visual element registry that tracks characters, objects, scenes, and their shot-level states. A VLM-annotated keyframe library further maps these elements to past visual observations. Guided by the required elements, our agent retrieves complementary references that maximize target-element coverage while minimizing historical noise. Finally, the retrieved references, structured element states, and grounding instructions are assembled into a unified prompt for the frozen video generator. This element-aware process provides comprehensive conditioning while remaining fully interpretable. Quantitative and qualitative evaluations on multi-shot story generation demonstrate that our method consistently outperforms recent-frame, memory-based, and entity-level retrieval baselines in cross-shot consistency and text-controllability.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-30 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.37407 — 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 2026-10-07T18:04:24.871Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).