Enregistré dans:
Détails bibliographiques
Auteurs principaux: Nazarenus, Jakob, Michels, Dominik, Palubicki, Wojtek, Kou, Simin, Zhang, Fang-Lue, Pirk, Soren, Koch, Reinhard
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2511.22459
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866912734417780736
author Nazarenus, Jakob
Michels, Dominik
Palubicki, Wojtek
Kou, Simin
Zhang, Fang-Lue
Pirk, Soren
Koch, Reinhard
author_facet Nazarenus, Jakob
Michels, Dominik
Palubicki, Wojtek
Kou, Simin
Zhang, Fang-Lue
Pirk, Soren
Koch, Reinhard
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2511_22459
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Gaussians on Fire: High-Frequency Reconstruction of Flames
Nazarenus, Jakob
Michels, Dominik
Palubicki, Wojtek
Kou, Simin
Zhang, Fang-Lue
Pirk, Soren
Koch, Reinhard
Computer Vision and Pattern Recognition
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.
title Gaussians on Fire: High-Frequency Reconstruction of Flames
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2511.22459