Physically realistic video editing from natural language instructions

Hsu, Hao-Yu

Permalink

https://hdl.handle.net/2142/129197 Copy

Description

Title

Physically realistic video editing from natural language instructions

Author(s)

Hsu, Hao-Yu

Issue Date

2025-04-15

Director of Research (if dissertation) or Advisor (if thesis)

Wang, Shenlong

Department of Study

Siebel School Comp & Data Sci

Discipline

Computer Science

Degree Granting Institution

University of Illinois Urbana-Champaign

Degree Name

M.S.

Degree Level

Thesis

Keyword(s)

• Visual effects
• text-guided video editing
• 3D simulation
• physical-based editing

Abstract

Modern visual effects (VFX) software has made it possible for skilled artists to create imagery of virtually anything. However, the creation process remains laborious, complex, and largely inaccessible to everyday users. In this work, we present AutoVFX, a framework that automatically creates realistic and dynamic VFX videos from a single video and natural language instructions. By carefully integrating neural scene modeling, LLM-based code generation, and physical simulation, AutoVFX is able to provide physically-grounded, photorealistic editing effects that can be controlled directly using natural language instructions. We conduct extensive experiments to validate AutoVFX’s efficacy across a diverse spectrum of videos and instructions. Quantitative and qualitative results suggest that AutoVFX outperforms all competing methods by a large margin in generative quality, instruction alignment, editing versatility, and physical plausibility.

Graduation Semester

2025-05

Type of Resource

Thesis

Handle URL

https://hdl.handle.net/2142/129197

Copyright and License Information

© 2025 Hao-Yu Hsu.

Owning Collections