FieryGS: In-the-Wild Fire Synthesis with Physics-Integrated Gaussian Splatting

2026-04-30

AI Summary

This work addresses the long-standing challenge of synthesizing realistic and physically plausible fire effects in real-world 3D scenes, which has traditionally relied on labor-intensive manual modeling and expert-driven parameter tuning, limiting scalability. We propose the first fully automatic method that integrates multimodal large language models for physical material inference with efficient volumetric combustion simulation, 3D Gaussian Splatting (3DGS) scene reconstruction, and a unified flame-scene rendering framework. Our approach generates high-fidelity, physically consistent, and user-controllable fire effects without any human intervention. Extensive evaluations across diverse indoor and outdoor environments demonstrate significant improvements over existing techniques, achieving state-of-the-art performance in visual realism, physical accuracy, and controllability.

Abstract

We consider the problem of synthesizing photorealistic, physically plausible combustion effects in in-the-wild 3D scenes. Traditional CFD and graphics pipelines can produce realistic fire effects but rely on handcrafted geometry, expert-tuned parameters, and labor-intensive workflows, limiting their scalability to the real world. Recent scene modeling advances like 3D Gaussian Splatting (3DGS) enable high-fidelity real-world scene reconstruction, yet lack physical grounding for combustion. To bridge this gap, we propose FieryGS, a physically-based framework that integrates physically-accurate and user-controllable combustion simulation and rendering within the 3DGS pipeline, enabling realistic fire synthesis for real scenes. Our approach tightly couples three key modules: (1) multimodal large-language-model-based physical material reasoning, (2) efficient volumetric combustion simulation, and (3) a unified renderer for fire and 3DGS. By unifying reconstruction, physical reasoning, simulation, and rendering, FieryGS removes manual tuning and automatically generates realistic, controllable fire dynamics consistent with scene geometry and materials. Our framework supports complex combustion phenomena -- including flame propagation, smoke dispersion, and surface carbonization -- with precise user control over fire intensity, airflow, ignition location and other combustion parameters. Evaluated on diverse indoor and outdoor scenes, FieryGS outperforms all comparative baselines in visual realism, physical fidelity, and controllability. Project page can be found at https://pku-vcl-geometry.github.io/FieryGS/.

Problem

• fire synthesis
• physically plausible
• in-the-wild 3D scenes
• combustion effects
• photorealistic

Innovation

• Physics-Integrated Gaussian Splatting
• Combustion Simulation
• Multimodal LLM Reasoning
• In-the-Wild Fire Synthesis
• Unified Rendering