ThermalGaussian: Thermal 3D Gaussian Splatting

Rongfeng Lu, Hangyu Chen, Zunjie Zhu, Yuhang Qin, Ming Lu, Le Zhang, Chenggang Yan, Anke Xue
{"title":"ThermalGaussian: Thermal 3D Gaussian Splatting","authors":"Rongfeng Lu, Hangyu Chen, Zunjie Zhu, Yuhang Qin, Ming Lu, Le Zhang, Chenggang Yan, Anke Xue","doi":"arxiv-2409.07200","DOIUrl":null,"url":null,"abstract":"Thermography is especially valuable for the military and other users of\nsurveillance cameras. Some recent methods based on Neural Radiance Fields\n(NeRF) are proposed to reconstruct the thermal scenes in 3D from a set of\nthermal and RGB images. However, unlike NeRF, 3D Gaussian splatting (3DGS)\nprevails due to its rapid training and real-time rendering. In this work, we\npropose ThermalGaussian, the first thermal 3DGS approach capable of rendering\nhigh-quality images in RGB and thermal modalities. We first calibrate the RGB\ncamera and the thermal camera to ensure that both modalities are accurately\naligned. Subsequently, we use the registered images to learn the multimodal 3D\nGaussians. To prevent the overfitting of any single modality, we introduce\nseveral multimodal regularization constraints. We also develop smoothing\nconstraints tailored to the physical characteristics of the thermal modality.\nBesides, we contribute a real-world dataset named RGBT-Scenes, captured by a\nhand-hold thermal-infrared camera, facilitating future research on thermal\nscene reconstruction. We conduct comprehensive experiments to show that\nThermalGaussian achieves photorealistic rendering of thermal images and\nimproves the rendering quality of RGB images. With the proposed multimodal\nregularization constraints, we also reduced the model's storage cost by 90\\%.\nThe code and dataset will be released.","PeriodicalId":501130,"journal":{"name":"arXiv - CS - Computer Vision and Pattern Recognition","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - CS - Computer Vision and Pattern Recognition","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.07200","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

Thermography is especially valuable for the military and other users of surveillance cameras. Some recent methods based on Neural Radiance Fields (NeRF) are proposed to reconstruct the thermal scenes in 3D from a set of thermal and RGB images. However, unlike NeRF, 3D Gaussian splatting (3DGS) prevails due to its rapid training and real-time rendering. In this work, we propose ThermalGaussian, the first thermal 3DGS approach capable of rendering high-quality images in RGB and thermal modalities. We first calibrate the RGB camera and the thermal camera to ensure that both modalities are accurately aligned. Subsequently, we use the registered images to learn the multimodal 3D Gaussians. To prevent the overfitting of any single modality, we introduce several multimodal regularization constraints. We also develop smoothing constraints tailored to the physical characteristics of the thermal modality. Besides, we contribute a real-world dataset named RGBT-Scenes, captured by a hand-hold thermal-infrared camera, facilitating future research on thermal scene reconstruction. We conduct comprehensive experiments to show that ThermalGaussian achieves photorealistic rendering of thermal images and improves the rendering quality of RGB images. With the proposed multimodal regularization constraints, we also reduced the model's storage cost by 90\%. The code and dataset will be released.
ThermalGaussian:热三维高斯拼接技术
热成像技术对于军队和其他监控摄像机用户尤为重要。最近提出了一些基于神经辐射场(NeRF)的方法,用于从一组热图像和 RGB 图像重建三维热场景。然而,与 NeRF 不同的是,3D 高斯拼接(3DGS)因其快速训练和实时渲染的特点而大行其道。在这项工作中,我们提出了 ThermalGaussian,这是第一种能够渲染 RGB 和热模式下高质量图像的热 3DGS 方法。我们首先校准 RGB 摄像机和红外热像仪,确保两种模式准确对齐。随后,我们使用注册图像来学习多模态 3D 高斯。为了防止任何单一模态的过度拟合,我们引入了多模态正则化约束。此外,我们还提供了一个名为 RGBT 场景的真实世界数据集,该数据集由手持式红外热像仪捕获,为未来的热场景重建研究提供了便利。我们进行了全面的实验,结果表明热高斯技术实现了热图像的逼真渲染,并提高了 RGB 图像的渲染质量。通过提出多模态规则化约束,我们还将模型的存储成本降低了90%。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信