PhysTalk: Language-driven Real-time Physics in 3D Gaussian Scenes
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 27 of its 42 references that are in the map. First posted on arXiv 31 Dec 2025.
Builds on
27 of 42 references.
References · 27
- 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
- 2023GPT-4 Technical Reportcited by 18,396
- 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
- 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
- 2021Program Synthesis with Large Language Modelscited by 3,637
- 2021Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fieldscited by 2,032
- 2022Reproducible scaling laws for contrastive language-image learningcited by 1,173
- 2022ProgPrompt: Generating Situated Robot Task Plans using Large Language Modelscited by 611
- 2022Visual Programming: Compositional visual reasoning without trainingcited by 516
- 2023Instruct-NeRF2NeRF: Editing 3D Scenes with Instructionscited by 484
- 2024Evaluating Text-to-Visual Generation with Image-to-Text Generationcited by 474
- 2023PhysGaussian: Physics-Integrated 3D Gaussians for Generative Dynamicscited by 377
15 more
- 2023GaussianEditor: Swift and Controllable 3D Editing with Gaussian Splattingcited by 335
- 2024VR-GS: A Physical Dynamics-Aware Interactive Gaussian Splatting System in Virtual Realitycited by 179
- 2024SceneCraft: An LLM Agent for Synthesizing 3D Scene as Blender Codecited by 134
- 2023GraphDreamer: Compositional 3D Scene Synthesis from Scene Graphscited by 97
- 2021A Neural Network Solves, Explains, and Generates University Math Problems by Program Synthesis and Few-Shot Learning at Human Levelcited by 96
- 2024DGE: Direct Gaussian 3D Editing by Consistent Multi-view Editingcited by 94
- 2024Editable Scene Simulation for Autonomous Driving via Collaborative LLM-Agentscited by 91
- 2023Octopus: Embodied Vision-Language Programmer from Environmental Feedbackcited by 73
- 2023GPT4Motion: Scripting Physical Motions in Text-to-Video Generation via Blender-Oriented GPT Planningcited by 61
- 2024Gaussian Splashing: Unified Particles for Versatile Motion Synthesis and Renderingcited by 37
- 2024AutoVFX: Physically Realistic Video Editing from Natural Language Instructionscited by 27
- 2023Dynamic Mesh-Aware Radiance Fieldscited by 21
- 2024Chat-Edit-3D: Interactive 3D Scene Editing via Text Promptscited by 19
- 2024Gaussians-to-Life: Text-Driven Animation of 3D Gaussian Splatting Scenescited by 9
- 2025PromptVFX: Text-Driven Fields for Open-World 3D Gaussian Animationcited by 4
Built on by
Citing papers per year: 2026: 3.
3 papers.
- 2026NEWTON: Agentic Planning for Physically Grounded Video Generationcited by 12
- 2026i-PhysGaussian: Implicit Physical Simulation for 3D Gaussian Splattingcited by 3
- 2026A differentiable Lagrangian-coupled 3D Gaussian Splatting-SPH model for forward simulation and inverse analysis in solid mechanicscited by 0
- 2026A differentiable Lagrangian-coupled 3D Gaussian Splatting-SPH model for forward simulation and inverse analysis in solid mechanics3 Oct 2026
- 2026NEWTON: Agentic Planning for Physically Grounded Video Generation18 May 2026
- 2026i-PhysGaussian: Implicit Physical Simulation for 3D Gaussian Splatting19 Feb 2026