Ambient-NeRF: light train enhancing neural radiance fields in low-light conditions with ambient-illumination

IF 3 4区 计算机科学 Q2 COMPUTER SCIENCE, INFORMATION SYSTEMS
Peng Zhang, Gengsheng Hu, Mei Chen, Mahmoud Emam
{"title":"Ambient-NeRF: light train enhancing neural radiance fields in low-light conditions with ambient-illumination","authors":"Peng Zhang, Gengsheng Hu, Mei Chen, Mahmoud Emam","doi":"10.1007/s11042-024-19699-3","DOIUrl":null,"url":null,"abstract":"<p>NeRF can render photorealistic 3D scenes. It is widely used in virtual reality, autonomous driving, game development and other fields, and quickly becomes one of the most popular technologies in the field of 3D reconstruction. NeRF generates a realistic 3D scene by emitting light from the camera’s spatial coordinates and viewpoint, passing through the scene and calculating the view seen from the viewpoint. However, when the brightness of the original input image is low, it is difficult to recover the scene. Inspired by the ambient illumination in the Phong model of computer graphics, it is assumed that the final rendered image is the product of scene color and ambient illumination. In this paper, we employ Multi-Layer Perceptron (MLP) network to train the ambient illumination tensor <span>\\(\\textbf{I}\\)</span>, which is multiplied by the color predicted by NeRF to render images with normal illumination. Furthermore, we use tiny-cuda-nn as a backbone network to simplify the proposed network structure and greatly improve the training speed. Additionally, a new loss function is introduced to achieve a better image quality under low illumination conditions. The experimental results demonstrate the efficiency of the proposed method in enhancing low-light scene images compared with other state-of-the-art methods, with an overall average of PSNR: 20.53 , SSIM: 0.785, and LPIPS: 0.258 on the LOM dataset.</p>","PeriodicalId":18770,"journal":{"name":"Multimedia Tools and Applications","volume":null,"pages":null},"PeriodicalIF":3.0000,"publicationDate":"2024-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Multimedia Tools and Applications","FirstCategoryId":"94","ListUrlMain":"https://doi.org/10.1007/s11042-024-19699-3","RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"COMPUTER SCIENCE, INFORMATION SYSTEMS","Score":null,"Total":0}
引用次数: 0

Abstract

NeRF can render photorealistic 3D scenes. It is widely used in virtual reality, autonomous driving, game development and other fields, and quickly becomes one of the most popular technologies in the field of 3D reconstruction. NeRF generates a realistic 3D scene by emitting light from the camera’s spatial coordinates and viewpoint, passing through the scene and calculating the view seen from the viewpoint. However, when the brightness of the original input image is low, it is difficult to recover the scene. Inspired by the ambient illumination in the Phong model of computer graphics, it is assumed that the final rendered image is the product of scene color and ambient illumination. In this paper, we employ Multi-Layer Perceptron (MLP) network to train the ambient illumination tensor \(\textbf{I}\), which is multiplied by the color predicted by NeRF to render images with normal illumination. Furthermore, we use tiny-cuda-nn as a backbone network to simplify the proposed network structure and greatly improve the training speed. Additionally, a new loss function is introduced to achieve a better image quality under low illumination conditions. The experimental results demonstrate the efficiency of the proposed method in enhancing low-light scene images compared with other state-of-the-art methods, with an overall average of PSNR: 20.53 , SSIM: 0.785, and LPIPS: 0.258 on the LOM dataset.

Abstract Image

环境-神经辐射场:用环境照明增强弱光条件下神经辐射场的光列
NeRF 可以渲染逼真的 3D 场景。它被广泛应用于虚拟现实、自动驾驶、游戏开发等领域,并迅速成为三维重建领域最流行的技术之一。NeRF 通过摄像机的空间坐标和视点发射光线,穿过场景并计算从视点看到的景象,从而生成逼真的三维场景。然而,当原始输入图像亮度较低时,很难复原场景。受计算机图形学 Phong 模型中环境光照的启发,假设最终渲染的图像是场景颜色和环境光照的乘积。在本文中,我们采用多层感知器(MLP)网络来训练环境光照张量(\textbf{I}\),并将其与 NeRF 预测的颜色相乘,从而渲染出具有正常光照的图像。此外,我们使用 tiny-cuda-nn 作为骨干网络,简化了所提出的网络结构,大大提高了训练速度。此外,我们还引入了一个新的损失函数,以便在低照度条件下获得更好的图像质量。实验结果表明,与其他最先进的方法相比,所提出的方法在增强低照度场景图像方面非常有效,在 LOM 数据集上的总体平均 PSNR 为 20.53,SSIM 为 0.785,LPIPS 为 0.258。
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
Multimedia Tools and Applications
Multimedia Tools and Applications 工程技术-工程:电子与电气
CiteScore
7.20
自引率
16.70%
发文量
2439
审稿时长
9.2 months
期刊介绍: Multimedia Tools and Applications publishes original research articles on multimedia development and system support tools as well as case studies of multimedia applications. It also features experimental and survey articles. The journal is intended for academics, practitioners, scientists and engineers who are involved in multimedia system research, design and applications. All papers are peer reviewed. Specific areas of interest include: - Multimedia Tools: - Multimedia Applications: - Prototype multimedia systems and platforms
×
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