FieryGS: In-the-Wild Fire Synthesis with Physics-Integrated Gaussian Splatting
Qianfan Shen, Ningxiao Tao, Qiyu Dai, Tianle Chen, Minghan Qin, Yongjie Zhang, Mengyu Chu, Wenzheng Chen, Baoquan Chen
摘要
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/ . Increasing time steps and rotating viewpoints Fiery GS Fiery GS Multi-view Inputs Figure 1: FieryGS synthesizes physically-grounded fire effects from multi-view image, enabling controllable and realistic fire for in-the-wild scenes.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
它引用的顶会 Paper18
- Segment AnythingAlexander Kirillov, Eric Mintun, Nikhila Ravi, Hanzi Mao 等ICCV 2023 · 被引用 13,211 次
- Diffusion Models Beat GANs on Image SynthesisPrafulla Dhariwal, Alexander Quinn NicholNeurIPS 2021 · 被引用 13,211 次
- 3D Gaussian Splatting for Real-Time Radiance Field RenderingBernhard Kerbl, Georgios Kopanas, Thomas Leimkühler, George DrettakisSIGGRAPH 2023 · 被引用 5,687 次
- SDEdit: Guided Image Synthesis and Editing with Stochastic Differential EquationsChenlin Meng, Yutong He, Yang Song, Jiaming Song 等ICLR 2022 · 被引用 2,128 次
- Nerfies: Deformable Neural Radiance FieldsKeunhong Park, Utkarsh Sinha, Jonathan T. Barron, Sofien Bouaziz 等ICCV 2021 · 被引用 1,442 次
相关 Paper
- Holistic Large-Scale Scene Reconstruction via Mixed Gaussian SplattingChuandong Liu, Huijiao Wang, Lei Yu, Gui-Song XiaNeurIPS 2025 · 被引用 4 次
- Gaussian Splashing: Unified Particles for Versatile Motion Synthesis and RenderingYutao Feng, Xiang Feng, Yintong Shang, Ying Jiang 等CVPR 2025
- PhysIR-Splat: Physically Consistent Thermal Infrared Radiative Transfer in 3D Gaussian SplattingJingyuan Gao, Yumeng Hu, Fei Gao, Mingjin ZhangCVPR 2026
- SGS-Intrinsic: Semantic-Invariant Gaussian Splatting for Sparse-View Indoor Inverse RenderingJiahao Niu, Rongjia Zheng, Wenju Xu, Wei-Shi Zheng 等CVPR 2026 · 被引用 1 次
- GS-IR: 3D Gaussian Splatting for Inverse RenderingZhihao Liang, Qi Zhang, Ying Feng, Ying Shan 等CVPR 2024
