FilmSceneDesigner: Chaining Set Design for Procedural Film Scene Generation

2025-11-24

AI Summary

To address the inefficiency and expert dependency of manual 3D scene modeling for film production, this paper proposes a natural language–driven automated 3D scene generation framework. Methodologically, it introduces a chain-of-agents architecture coupled with a hierarchical prompting strategy to enable precise, structured inference of cinematic parameters—including scene type, historical period, and artistic style. Integrated with SetDepot-Pro, a film-industry–specific 3D asset library, and a procedural generation pipeline, the system supports end-to-end 3D reconstruction encompassing spatial layout, material assignment, and object placement. The generated scenes exhibit high cinematic fidelity and structural plausibility, directly supporting virtual previsualization, construction drawing generation, and mood board creation. Human evaluation and experimental validation demonstrate significant improvements over baseline methods in semantic consistency, visual realism, and design usability.

Technology Category

Natural Language Processing: GenerationHumans and AI: Game Design — Procedural Content Generation & StorytellingComputer Vision: 3D Computer Vision

Application Category

Economics, Online Markets and Human Computation: Cost models of using LLMs in production systemsSemantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactionsSocial Networks and Social Media: Generative AI / large language models and their impact on social systems

Abstract

Film set design plays a pivotal role in cinematic storytelling and shaping the visual atmosphere. However, the traditional process depends on expert-driven manual modeling, which is labor-intensive and time-consuming. To address this issue, we introduce FilmSceneDesigner, an automated scene generation system that emulates professional film set design workflow. Given a natural language description, including scene type, historical period, and style, we design an agent-based chaining framework to generate structured parameters aligned with film set design workflow, guided by prompt strategies that ensure parameter accuracy and coherence. On the other hand, we propose a procedural generation pipeline which executes a series of dedicated functions with the structured parameters for floorplan and structure generation, material assignment, door and window placement, and object retrieval and layout, ultimately constructing a complete film scene from scratch. Moreover, to enhance cinematic realism and asset diversity, we construct SetDepot-Pro, a curated dataset of 6,862 film-specific 3D assets and 733 materials. Experimental results and human evaluations demonstrate that our system produces structurally sound scenes with strong cinematic fidelity, supporting downstream tasks such as virtual previs, construction drawing and mood board creation.

Problem

• Automates labor-intensive manual film set design process
• Generates complete film scenes from natural language descriptions
• Enhances cinematic realism through curated 3D assets dataset

Innovation

• Agent-based chaining framework for structured parameter generation
• Procedural pipeline for floorplan generation and object layout
• Curated dataset of film-specific 3D assets and materials