Gaussians on Fire: High-Frequency Reconstruction of Flames

2025-11-27

AI Summary

Reconstructing dynamic, transparent, and high-frequency flame geometry from only three viewpoints is challenging due to weak geometric constraints. Method: We propose a 3D Gaussian-based dynamic flame reconstruction framework featuring (i) Gaussian lifetime and linear velocity modeling; (ii) joint multi-view stereo matching and monocular depth priors to decouple flame from background; (iii) dense optical flow projection for spatiotemporally consistent flame motion fields; and (iv) hardware synchronization for precise inter-frame temporal alignment. Contribution/Results: Compared with voxel- or NeRF-based representations, our method significantly improves fidelity in reconstructing high-frequency structural details and dynamic motion. Extensive qualitative and quantitative evaluations on diverse real-world flame scenes demonstrate robustness and practicality. This work establishes a novel paradigm for dynamic transparent object reconstruction under sparse-view conditions.

Technology Category

• Computer Vision: 3D Computer Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Security and Privacy: Data transparency and provenance
• Systems and Infrastructure for Web, Mobile and WoT: Data management and stream processing for Web, mobile and wireless applications

Abstract

We propose a method to reconstruct dynamic fire in 3D from a limited set of camera views with a Gaussian-based spatiotemporal representation. Capturing and reconstructing fire and its dynamics is highly challenging due to its volatile nature, transparent quality, and multitude of high-frequency features. Despite these challenges, we aim to reconstruct fire from only three views, which consequently requires solving for under-constrained geometry. We solve this by separating the static background from the dynamic fire region by combining dense multi-view stereo images with monocular depth priors. The fire is initialized as a 3D flow field, obtained by fusing per-view dense optical flow projections. To capture the high frequency features of fire, each 3D Gaussian encodes a lifetime and linear velocity to match the dense optical flow. To ensure sub-frame temporal alignment across cameras we employ a custom hardware synchronization pattern -- allowing us to reconstruct fire with affordable commodity hardware. Our quantitative and qualitative validations across numerous reconstruction experiments demonstrate robust performance for diverse and challenging real fire scenarios.

Problem

• Reconstruct dynamic fire in 3D from limited camera views
• Solve under-constrained geometry using only three views
• Capture high-frequency fire features with Gaussian-based representation

Innovation

• Gaussian-based spatiotemporal representation for dynamic fire
• Separating static background using multi-view stereo and depth priors
• Hardware synchronization for sub-frame temporal alignment