PromptVFX: Text-Driven Fields for Open-World 3D Gaussian Animation
This work addresses the time-consuming and expertise-intensive process of 3D animation for films, games, and AR/VR, offering a fast and accessible solution that could democratize VFX creation.
The paper tackles the problem of creating 3D visual effects (VFX) by introducing a text-driven framework that infers a 4D flow field to animate 3D Gaussians in real time, enabling novice and expert users to generate effects like glowing or exploding objects with minimal effort on consumer devices.
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.