CamPilot: A Multi-Agent Cinematic Assistant for Camera-Controlled Movie Generation

Researchers introduced CamPilot, a multi-agent framework that integrates cinematographic planning and camera-work control to generate more coherent, logically structured movies, trained via a GRPO-based learning paradigm on 14K real-world professional movies. The team also established CamEval, a benchmark for evaluating camera work quality and cinematic engagement, and reported that CamPilot outperforms state-of-the-art text-to-movie generation methods on cinematographic control and quality.

arXiv:2609.10943v1 Announce Type: new Abstract: 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.