Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2603.14790 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911552005734400 |
|---|---|
| author | Nan, Shufeng Li, Mengtian Zheng, Sixiao Lu, Yuwei Zhang, Han Fu, Yanwei |
| author_facet | Nan, Shufeng Li, Mengtian Zheng, Sixiao Lu, Yuwei Zhang, Han Fu, Yanwei |
| contents | We present Mind-of-Director, a multi-modal agent-driven framework for film previz that models the collaborative decision-making process of a film production team. Given a creative idea, Mind-of-Director orchestrates multiple specialized agents to produce previz sequences within the game engine. The framework consists of four cooperative modules: Script Development, where agents draft and refine the screenplay iteratively; Virtual Scene Design, which transforms text into semantically aligned 3D environments; Character Behaviour Control, which determines character blocking and motion; and Camera Planning, which optimizes framing, movement, and composition for cinematic camera effects. A real-time visual editing system built in the game engine further enables interactive inspection and synchronized timeline adjustment across scenes, behaviours, and cameras. Extensive experiments and human evaluations show that Mind-of-Director generates high-quality, semantically grounded previz sequences in approximately 25 minutes per idea, demonstrating the effectiveness of agent collaboration for both automated prototyping and human-in-the-loop filmmaking. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_14790 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Mind-of-Director: Multi-modal Agent-Driven Film Previsualization via Collaborative Decision-Making Nan, Shufeng Li, Mengtian Zheng, Sixiao Lu, Yuwei Zhang, Han Fu, Yanwei Computer Vision and Pattern Recognition We present Mind-of-Director, a multi-modal agent-driven framework for film previz that models the collaborative decision-making process of a film production team. Given a creative idea, Mind-of-Director orchestrates multiple specialized agents to produce previz sequences within the game engine. The framework consists of four cooperative modules: Script Development, where agents draft and refine the screenplay iteratively; Virtual Scene Design, which transforms text into semantically aligned 3D environments; Character Behaviour Control, which determines character blocking and motion; and Camera Planning, which optimizes framing, movement, and composition for cinematic camera effects. A real-time visual editing system built in the game engine further enables interactive inspection and synchronized timeline adjustment across scenes, behaviours, and cameras. Extensive experiments and human evaluations show that Mind-of-Director generates high-quality, semantically grounded previz sequences in approximately 25 minutes per idea, demonstrating the effectiveness of agent collaboration for both automated prototyping and human-in-the-loop filmmaking. |
| title | Mind-of-Director: Multi-modal Agent-Driven Film Previsualization via Collaborative Decision-Making |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.14790 |