FlameGS: Reconstruct flame light field via Gaussian Splatting

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Shui, Yunhao, Zhang, Fuhao, Gao, Can, Xue, Hao, Ma, Zhiyin, Xun, Gang, Li, Xuesong
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910765075660800
author Shui, Yunhao
Zhang, Fuhao
Gao, Can
Xue, Hao
Ma, Zhiyin
Xun, Gang
Li, Xuesong
author_facet Shui, Yunhao
Zhang, Fuhao
Gao, Can
Xue, Hao
Ma, Zhiyin
Xun, Gang
Li, Xuesong
contents To address the time-consuming and computationally intensive issues of traditional ART algorithms for flame combustion diagnosis, inspired by flame simulation technology, we propose a novel representation method for flames. By modeling the luminous process of flames and utilizing 2D projection images for supervision, our experimental validation shows that this model achieves an average structural similarity index of 0.96 between actual images and predicted 2D projections, along with a Peak Signal-to-Noise Ratio of 39.05. Additionally, it saves approximately 34 times the computation time and about 10 times the memory compared to traditional algorithms.
format Preprint
id arxiv_https___arxiv_org_abs_2412_19841
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle FlameGS: Reconstruct flame light field via Gaussian Splatting
Shui, Yunhao
Zhang, Fuhao
Gao, Can
Xue, Hao
Ma, Zhiyin
Xun, Gang
Li, Xuesong
Computer Vision and Pattern Recognition
Image and Video Processing
To address the time-consuming and computationally intensive issues of traditional ART algorithms for flame combustion diagnosis, inspired by flame simulation technology, we propose a novel representation method for flames. By modeling the luminous process of flames and utilizing 2D projection images for supervision, our experimental validation shows that this model achieves an average structural similarity index of 0.96 between actual images and predicted 2D projections, along with a Peak Signal-to-Noise Ratio of 39.05. Additionally, it saves approximately 34 times the computation time and about 10 times the memory compared to traditional algorithms.
title FlameGS: Reconstruct flame light field via Gaussian Splatting
topic Computer Vision and Pattern Recognition
Image and Video Processing
url https://arxiv.org/abs/2412.19841