Metraipolis › archive › dc_de7561307c45
CamPilot: A Multi-Agent Cinematic Assistant for Camera-Controlled Movie Generation — arXiv:2609.10943
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.10943
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T06:35:12.954Z
- SHA-256 of the archived text
c02d714af8679d21098c98f4f1d56683b6f1be004b04dcfa4c48847c2a40a9fb- Stable URL of this page
https://metraipolis.com/documento/dc_de7561307c45
How to cite
CamPilot: A Multi-Agent Cinematic Assistant for Camera-Controlled Movie Generation — arXiv:2609.10943 — arXiv (en), https://arxiv.org/abs/2609.10943 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_de7561307c45 (Metraipolis archive dc_de7561307c45, sha256 c02d714af8679d21098c98f4f1d56683b6f1be004b04dcfa4c48847c2a40a9fb)
BibTeX
@misc{dcde7561307c45,
title = {CamPilot: A Multi-Agent Cinematic Assistant for Camera-Controlled Movie Generation — arXiv:2609.10943},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.10943},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_de7561307c45; sha256 c02d714af8679d21098c98f4f1d56683b6f1be004b04dcfa4c48847c2a40a9fb},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.10943. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
The integration of large language models (LLMs) into video generation has enabled rapid text-to-video creation and improved visual quality. However, it still falls short of professional filmmaking, where cinematographic language is less refined than human-crafted camera work and multi-shot continuity remains challenging. To address these limitations, we introduce CamPilot, a multi-agent framework that integrates cinematographic planning and camera-work control to produce more coherent, logically structured, and human-aesthetic movies. CamPilot adopts a GRPO-based learning paradigm to learn camera work planning from 14K real-world professional movies, internalizing motion patterns and composition principles that support reasoning over shooting techniques (e.g., camera angle, motion, and focal behavior) and cross-shot relationships for controllable camera-viewpoint generation. Multiple agents further collaborate and evolve to improve overall output quality. To support this work and further studies in this domain, we establish CamEval, a benchmark for evaluating camera work quality and cinematic engagement. Empirical results show that CamPilot outperforms state-of-the-art text-to-movie generation methods on cinematographic control and quality, highlighting the impact of professional camera design on movie generation. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-11 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.10943 — 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 2026-10-16T06:06:28.751Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).