Date of Award

Spring 2026

Degree Type

Honors College Thesis

Academic Program

Computer Science BS

Department

Computing

First Advisor

Bo Li

Advisor Department

Computing

Abstract

Pre-visualization is a core part of film pre-production. Creators use it to test blocking, lighting, camera movement, and spatial relationships before committing to a shot. Despite this, three-dimensional pre-visualization remains out of reach for many entry-level filmmakers, as the software is expensive and takes substantial time to learn.

Recent AI developments have produced generative systems capable of creating highly re-alistic imagery and video from text prompts. These systems open new possibilities for visual sto-rytelling but are not built for the iterative, hands-on process that pre-visualization requires, where creators must adjust scene parameters, camera logic, and spatial configurations throughout.

This thesis develops an AI-assisted pipeline that connects screenplay text to editable 3D environments within Blender, reducing technical barriers while keeping creative control with the filmmaker. The system is evaluated through a user study and quantitative metrics, including gen-eration time, reliability, scalability, and required manual effort. By automating key stages of the workflow while preserving user control, the system reduces animatic production time by approxi-mately 85%, achieving a 6.7× speedup over fully manual methods. The result is a practical tool that lowers the barrier to 3D pre-vis for independent filmmakers, with implications for human-centered AI design in creative production.

Download

Share

COinS