PhysTalk: Language-driven Real-time Physics in 3D Gaussian Scenes
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908741608144896 |
|---|---|
| author | Collorone, Luca Kiray, Mert Spinelli, Indro Galasso, Fabio Busam, Benjamin |
| author_facet | Collorone, Luca Kiray, Mert Spinelli, Indro Galasso, Fabio Busam, Benjamin |
| contents | Realistic visual simulations are omnipresent, yet their creation requires computing time, rendering, and expert animation knowledge. Open-vocabulary visual effects generation from text inputs emerges as a promising solution that can unlock immense creative potential. However, current pipelines lack both physical realism and effective language interfaces, requiring slow offline optimization. In contrast, PhysTalk takes a 3D Gaussian Splatting (3DGS) scene as input and translates arbitrary user prompts into real time, physics based, interactive 4D animations. A large language model (LLM) generates executable code that directly modifies 3DGS parameters through lightweight proxies and particle dynamics. Notably, PhysTalk is the first framework to couple 3DGS directly with a physics simulator without relying on time consuming mesh extraction. While remaining open vocabulary, this design enables interactive 3D Gaussian animation via collision aware, physics based manipulation of arbitrary, multi material objects. Finally, PhysTalk is train-free and computationally lightweight: this makes 4D animation broadly accessible and shifts these workflows from a "render and wait" paradigm toward an interactive dialogue with a modern, physics-informed pipeline. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_24986 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | PhysTalk: Language-driven Real-time Physics in 3D Gaussian Scenes Collorone, Luca Kiray, Mert Spinelli, Indro Galasso, Fabio Busam, Benjamin Graphics Computer Vision and Pattern Recognition Realistic visual simulations are omnipresent, yet their creation requires computing time, rendering, and expert animation knowledge. Open-vocabulary visual effects generation from text inputs emerges as a promising solution that can unlock immense creative potential. However, current pipelines lack both physical realism and effective language interfaces, requiring slow offline optimization. In contrast, PhysTalk takes a 3D Gaussian Splatting (3DGS) scene as input and translates arbitrary user prompts into real time, physics based, interactive 4D animations. A large language model (LLM) generates executable code that directly modifies 3DGS parameters through lightweight proxies and particle dynamics. Notably, PhysTalk is the first framework to couple 3DGS directly with a physics simulator without relying on time consuming mesh extraction. While remaining open vocabulary, this design enables interactive 3D Gaussian animation via collision aware, physics based manipulation of arbitrary, multi material objects. Finally, PhysTalk is train-free and computationally lightweight: this makes 4D animation broadly accessible and shifts these workflows from a "render and wait" paradigm toward an interactive dialogue with a modern, physics-informed pipeline. |
| title | PhysTalk: Language-driven Real-time Physics in 3D Gaussian Scenes |
| topic | Graphics Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2512.24986 |