mlsanityData to 7 Oct 2026

Mind-of-Director: Multi-modal Agent-Driven Film Previsualization via Collaborative Decision-Making

arXiv 2603.14790 ↗First posted 16 Mar 2026cs.CVcited by 2

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 38 of its 50 references that are in the map. First posted on arXiv 16 Mar 2026.

Builds on

38 of 50 references.

References · 38

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2023Segment Anythingcited by 8,158
  3. 2022Objaverse: A Universe of Annotated 3D Objectscited by 1,522
  4. 2023Florence-2: Advancing a Unified Representation for a Variety of Vision Taskscited by 403
  5. 2022ProcTHOR: Large-Scale Embodied AI Using Procedural Generationcited by 369
  6. 2023LayoutGPT: Compositional Visual Planning and Generation with Large Language Modelscited by 337
  7. 2023ReconFusion: 3D Reconstruction with Diffusion Priorscited by 317
  8. 2023LucidDreamer: Towards High-Fidelity Text-to-3D Generation via Interval Score Matchingcited by 290
  9. 2023Holodeck: Language Guided Generation of 3D Embodied AI Environmentscited by 257
  10. 2024Infinigen Indoors: Photorealistic Indoor Scenes using Procedural Generationcited by 129
  11. 2024PhyScene: Physically Interactable 3D Scene Synthesis for Embodied AIcited by 116
  12. 2025CAST: Component-Aligned 3D Scene Reconstruction from an RGB Imagecited by 101
26 more
  1. 2024LayoutVLM: Differentiable Optimization of 3D Layout via Vision-Language Modelscited by 94
  2. 20233D-GPT: Procedural 3D Modeling with Large Language Modelscited by 91
  3. 2025Automated Movie Generation via Multi-Agent CoT Planningcited by 82
  4. 2024SEED-Story: Multimodal Long Story Generation with Large Language Modelcited by 70
  5. 2025Scenethesis: A Language and Vision Agentic Framework for 3D Scene Generationcited by 65
  6. 2025Towards Understanding Camera Motions in Any Videocited by 62
  7. 2025SceneGen: Single-Image 3D Scene Generation in One Feedforward Passcited by 49
  8. 2024DreamStory: Open-Domain Story Visualization by LLM-Guided Multi-Subject Consistent Diffusioncited by 46
  9. 2024Anim-Director: A Large Multimodal Model Powered Agent for Controllable Animation Video Generationcited by 35
  10. 2025FilMaster: Bridging Cinematic Principles and Generative AI for Automated Film Generationcited by 28
  11. 2024E.T. the Exceptional Trajectories: Text-to-camera-trajectory generation with character awarenesscited by 24
  12. 2025FirePlace: Geometric Refinements of LLM Common Sense Reasoning for 3D Object Placementcited by 24
  13. 2023Dynamic Storyboard Generation in an Engine-based Virtual Environment for Video Productioncited by 21
  14. 2025MAViS: A Multi-Agent Framework for Long-Sequence Video Storytellingcited by 19
  15. 2024Cinematographic Camera Diffusion Modelcited by 18
  16. 2024ChatCam: Empowering Camera Control through Conversational AIcited by 15
  17. 2025HOLODECK 2.0: Vision-Language-Guided 3D World Generation with Editingcited by 14
  18. 2021Finding the Right Moment: Human-Assisted Trailer Creation via Task Compositioncited by 12
  19. 2024Story3D-Agent: Exploring 3D Storytelling Visualization with Large Language Modelscited by 9
  20. 2024ContextualStory: Consistent Visual Storytelling with Spatially-Enhanced and Storyline Contextcited by 8
  21. 2024CinePreGen: Camera Controllable Video Previsualization via Engine-powered Diffusioncited by 7
  22. 2025VEU-Bench: Towards Comprehensive Understanding of Video Editingcited by 7
  23. 2024ScriptViz: A Visualization Tool to Aid Scriptwriting based on a Large Movie Databasecited by 6
  24. 2022Cine-AI: Generating Video Game Cutscenes in the Style of Human Directorscited by 5
  25. 2025VisAgent: Narrative-Preserving Story Visualization Frameworkcited by 4
  26. 2025StageDesigner: Artistic Stage Generation for Scenography via Theater Scriptscited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 2.

2 papers.