FilmFlow：将自然语言与参考视频转为 3D 虚拟摄影机轨迹的智能体系统

View PDF HTML (experimental)

Abstract:Complex camera motion is central to visual storytelling, yet translating cinematographic intent into controllable, executable camera trajectories remains challenging. We introduce FilmFlow, an agentic framework that converts natural-language instructions or reference videos into explicit camera trajectories for dynamic 3D environments. To generate these trajectories, a Director agent constructs executable camera plans by composing high-level motions from concurrent atomic operations that jointly control translation, rotation, and framing. The Director is supported by three specialized agents: an Interpreter that extracts scene-grounded cinematographic intent, a Scout that selects initial viewpoints, and a Critic that evaluates rendered results and provides visual feedback for iterative plan refinement. We also introduce CinemaBench, comprising 150 Blender scenes from self-created and licensed sources, with five camera instructions per scene for 750 text-directed tasks and 60 reference videos associated with a subset of scenes. CinemaBench supports evaluation of both text-directed camera generation and video reference-directed camera generation. Across a diverse set of evaluated baselines, FilmFlow achieves the strongest benchmark performance and the highest user preference, demonstrating effective spatial reasoning, temporal coordination, and visual composition for executable 3D cinematography.

Subjects:	Computer Vision and Pattern Recognition (cs.CV)
Cite as:	arXiv:2610.30753 [cs.CV]
	(or arXiv:2610.30753v1 [cs.CV] for this version)
	https://doi.org/10.48550/arXiv.2610.30753 arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Yiming Zhang [view email]
[v1] Thu, 22 Oct 2026 05:22:16 UTC (5,612 KB)