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

• URL: http://arxiv.org/abs/2605.00177v1
• Date: Thu, 30 Apr 2026 19:53:37 GMT
• Title: FieryGS: In-the-Wild Fire Synthesis with Physics-Integrated Gaussian Splatting
• Abstract summary: Traditional CFD and graphics pipelines produce realistic fire effects but rely on handcrafted geometry, expert-intensive parameters, and labor-intensive parameters.<n>Recent scene modeling advances like 3D Splatting enable high-fidelity real-world scene reconstruction, yet lack physical grounding for combustion.<n>We propose FieryGS, a framework that integrates physically-accurate and user-controllable combustion simulation and synthesizing within the 3DGS pipeline.
• Score: 31.462038725671054
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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/.

Related papers

• Scene-Level Heterogeneous Physics Simulation with 3D Gaussian Splats [32.12749945486662]
  3D Gaussian Splatting (3DGS) has achieved state-of-the-art rendering, but the representation gap prevents these assets from being physically interactive.<n>We propose a novel framework that bridges this gap by enabling 3DGS assets to participate in scene-level, heterogeneous, multi-solver physical simulations.<n>We demonstrate complex, two-way interactions between deformable 3DGS assets, standard CG assets such as fluids and meshes, and large-scale captured static environments.
  arXiv  Detail & Related papers  (2026-06-19T21:12:52Z)
• GS-Playground: A High-Throughput Photorealistic Simulator for Vision-Informed Robot Learning [55.272458304179025]
  GS-Playground is a multi-modal simulation framework designed to accelerate end-to-end perceptual learning.<n>Our system achieves a breakthrough throughput of 104 FPS at 640x480 resolution, significantly lowering the barrier for large-scale visual RL.
  arXiv  Detail & Related papers  (2026-04-28T10:05:39Z)
• LightHarmony3D: Harmonizing Illumination and Shadows for Object Insertion in 3D Gaussian Splatting [90.15229815175593]
  We present LightHarmony3D, a novel framework for illumination-consistent mesh insertion in 3DGS scenes.<n>By leveraging generative priors instead of iterative optimization, our method efficiently captures dominant scene illumination.<n>We introduce the first dedicated benchmark for mesh insertion in 3DGS, providing a standardized evaluation framework for assessing lighting consistency and photorealism.
  arXiv  Detail & Related papers  (2026-03-31T03:26:30Z)
• R-PGA: Robust Physical Adversarial Camouflage Generation via Relightable 3D Gaussian Splatting [59.29134814041703]
  Physical adversarial camouflage poses a severe security threat to autonomous driving systems.<n>Current methods fail to generalize across diverse geometric (e.g., viewing configurations) and radiometric variations.<n>We propose the Relightable Physical 3D Gaussian Splatting framework (R-PGA)
  arXiv  Detail & Related papers  (2026-03-27T04:38:04Z)
• SceMoS: Scene-Aware 3D Human Motion Synthesis by Planning with Geometry-Grounded Tokens [89.05195827071582]
  SceMoS is a scene-aware motion synthesis framework.<n>It disentangles global planning from local execution using lightweight 2D cues.<n>SceMoS achieves state-of-the-art motion realism and contact accuracy on the TRUMANS benchmark.
  arXiv  Detail & Related papers  (2026-02-24T02:09:12Z)
• Mirage2Matter: A Physically Grounded Gaussian World Model from Video [87.9732484393686]
  We present Simulate Anything, a graphics-driven world modeling and simulation framework.<n>Our approach reconstructs real-world environments into a photorealistic scene representation using 3D Gaussian Splatting (3DGS)<n>We then leverage generative models to recover a physically realistic representation and integrate it into a simulation environment via a precision calibration target.
  arXiv  Detail & Related papers  (2026-01-24T07:43:57Z)
• PhysFire-WM: A Physics-Informed World Model for Emulating Fire Spread Dynamics [46.81004231857954]
  This paper introduces PhysFire-WM, a Physics-informed World Model for emulating Fire spread dynamics.<n>Our approach internalizes combustion dynamics by encoding structured priors from a Physical Simulator to rectify physical discrepancies.<n>Experiments on a fine-grained multimodal fire dataset demonstrate the superior accuracy of PhysFire-WM in fire spread prediction.
  arXiv  Detail & Related papers  (2025-12-19T01:16:40Z)
• GS-Verse: Mesh-based Gaussian Splatting for Physics-aware Interaction in Virtual Reality [1.2271175670122132]
  Current techniques for physically manipulating 3D content within Virtual Reality (VR) often face significant limitations.<n>We introduce GS-Verse, a novel method designed to overcome these challenges by directly integrating an object's mesh with a Gaussian Splatting representation.<n>Our system is designed to be physics-engine-agnostic, granting developers robust deployment flexibility.
  arXiv  Detail & Related papers  (2025-10-13T19:36:47Z)
• ClimateGS: Real-Time Climate Simulation with 3D Gaussian Style Transfer [11.17376076195671]
  ClimateGS is a novel framework integrating 3D Gaussian representations with physical simulation to enable real-time climate effects rendering.<n>We evaluate ClimateGS on MipNeRF360 and Tanks and Temples, demonstrating real-time rendering with comparable or superior visual quality to SOTA 2D/3D methods.
  arXiv  Detail & Related papers  (2025-03-19T03:01:35Z)
• EndoPBR: Material and Lighting Estimation for Photorealistic Surgical Simulations via Physically-based Rendering [1.03590082373586]
  The lack of labeled datasets in 3D vision for surgical scenes inhibits the development of robust 3D reconstruction algorithms.<n>We introduce a differentiable rendering framework for material and lighting estimation from endoscopic images and known geometry.<n>By grounding color predictions in the rendering equation, we can generate photorealistic images at arbitrary camera poses.
  arXiv  Detail & Related papers  (2025-02-28T02:50:59Z)
• Intrinsic Autoencoders for Joint Neural Rendering and Intrinsic Image Decomposition [67.9464567157846]
  We propose an autoencoder for joint generation of realistic images from synthetic 3D models while simultaneously decomposing real images into their intrinsic shape and appearance properties. Our experiments confirm that a joint treatment of rendering and decomposition is indeed beneficial and that our approach outperforms state-of-the-art image-to-image translation baselines both qualitatively and quantitatively.
  arXiv  Detail & Related papers  (2020-06-29T12:53:58Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.