PromptVFX: Text-Driven Fields for Open-World 3D Gaussian Animation

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Kiray, Mert, Uhlenbruck, Paul, Navab, Nassir, Busam, Benjamin
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911403089068032
author Kiray, Mert
Uhlenbruck, Paul
Navab, Nassir
Busam, Benjamin
author_facet Kiray, Mert
Uhlenbruck, Paul
Navab, Nassir
Busam, Benjamin
contents Visual effects (VFX) are key to immersion in modern films, games, and AR/VR. Creating 3D effects requires specialized expertise and training in 3D animation software and can be time consuming. Generative solutions typically rely on computationally intense methods such as diffusion models which can be slow at 4D inference. We reformulate 3D animation as a field prediction task and introduce a text-driven framework that infers a time-varying 4D flow field acting on 3D Gaussians. By leveraging large language models (LLMs) and vision-language models (VLMs) for function generation, our approach interprets arbitrary prompts (e.g., "make the vase glow orange, then explode") and instantly updates color, opacity, and positions of 3D Gaussians in real time. This design avoids overheads such as mesh extraction, manual or physics-based simulations and allows both novice and expert users to animate volumetric scenes with minimal effort on a consumer device even in a web browser. Experimental results show that simple textual instructions suffice to generate compelling time-varying VFX, reducing the manual effort typically required for rigging or advanced modeling. We thus present a fast and accessible pathway to language-driven 3D content creation that can pave the way to democratize VFX further. Code available at https://obsphera.github.io/promptvfx/.
format Preprint
id arxiv_https___arxiv_org_abs_2506_01091
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle PromptVFX: Text-Driven Fields for Open-World 3D Gaussian Animation
Kiray, Mert
Uhlenbruck, Paul
Navab, Nassir
Busam, Benjamin
Graphics
Computer Vision and Pattern Recognition
Visual effects (VFX) are key to immersion in modern films, games, and AR/VR. Creating 3D effects requires specialized expertise and training in 3D animation software and can be time consuming. Generative solutions typically rely on computationally intense methods such as diffusion models which can be slow at 4D inference. We reformulate 3D animation as a field prediction task and introduce a text-driven framework that infers a time-varying 4D flow field acting on 3D Gaussians. By leveraging large language models (LLMs) and vision-language models (VLMs) for function generation, our approach interprets arbitrary prompts (e.g., "make the vase glow orange, then explode") and instantly updates color, opacity, and positions of 3D Gaussians in real time. This design avoids overheads such as mesh extraction, manual or physics-based simulations and allows both novice and expert users to animate volumetric scenes with minimal effort on a consumer device even in a web browser. Experimental results show that simple textual instructions suffice to generate compelling time-varying VFX, reducing the manual effort typically required for rigging or advanced modeling. We thus present a fast and accessible pathway to language-driven 3D content creation that can pave the way to democratize VFX further. Code available at https://obsphera.github.io/promptvfx/.
title PromptVFX: Text-Driven Fields for Open-World 3D Gaussian Animation
topic Graphics
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2506.01091