Gaussians on Fire: High-Frequency Reconstruction of Flames

TL;DR

This paper introduces a novel method for 3D reconstruction of dynamic fire using limited camera views by employing Gaussian-based spatiotemporal representations and optical flow, enabling detailed fire modeling with affordable hardware.

Contribution

It presents a new approach combining Gaussian representations, optical flow, and hardware synchronization to reconstruct high-frequency fire dynamics from minimal views.

Findings

Robust reconstruction of fire from only three views.

Effective separation of static background and fire regions.

High-quality results validated on diverse fire scenarios.

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.