• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利:CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法,用中文像聊天一样搜索,搜遍4000万医学文献。AI智能推荐,让科研检索更轻松。

立即免费搜索

文件翻译

保留排版,准确专业,支持PDF/Word/PPT等文件格式,支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述,25分钟生成高质量综述,智能提取关键信息,辅助科研写作。

立即免费体验

关于通过二维和三维高斯点云渲染增强的结构光运动法对透明表面进行几何三维重建的度量误差评估

Metric Error Assessment Regarding Geometric 3D Reconstruction of Transparent Surfaces via SfM Enhanced by 2D and 3D Gaussian Splatting.

作者信息

Billi Dario, Caroti Gabriella, Piemonte Andrea

机构信息

ASTRO Laboratory, Department of Civil and Industrial Engineering, University of Pisa, L.go Lucio Lazzarino, 56122 Pisa, Italy.

出版信息

Sensors (Basel). 2025 Jul 15;25(14):4410. doi: 10.3390/s25144410.

DOI:10.3390/s25144410
PMID:40732537
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC12300396/
Abstract

This research investigates the metric accuracy of 3D transparent object reconstruction, a task where conventional photogrammetry often fails. The topic is especially relevant in cultural heritage (CH), where accurate digital documentation of glass and transparent artifacts is important. The work proposes a practical methodology using existing tools to verify metric accuracy standards. The study compares three methods, conventional photogrammetry, 3D Gaussian splatting (3DGS), and 2D Gaussian splatting (2DGS), to assess their ability to produce complete and metrically reliable 3D models suitable for measurement and geometric analysis. A transparent glass artifact serves as the case study. Results show that 2DGS captures fine surface and internal details with better geometric consistency than 3DGS and photogrammetry. Although 3DGS offers high visual quality, it introduces surface artifacts that affect metric reliability. Photogrammetry fails to reconstruct the object entirely. The study highlights that visual quality does not ensure geometric accuracy, which is critical for measurement applications. In this work, ground truth comparisons confirm that 2DGS offers the best trade-off between accuracy and appearance, despite higher computational demands. These findings suggest extending the experimentation to other sets of images featuring transparent objects, and possibly also reflective ones.

摘要

本研究调查了三维透明物体重建的度量准确性,这是一项传统摄影测量常常无法完成的任务。该主题在文化遗产领域尤为相关,其中玻璃和透明文物的精确数字记录非常重要。这项工作提出了一种使用现有工具来验证度量准确性标准的实用方法。该研究比较了三种方法,即传统摄影测量、三维高斯点云渲染(3DGS)和二维高斯点云渲染(2DGS),以评估它们生成适用于测量和几何分析的完整且度量可靠的三维模型的能力。一个透明玻璃文物用作案例研究。结果表明,与3DGS和摄影测量相比,2DGS能以更好的几何一致性捕捉精细的表面和内部细节。尽管3DGS提供了较高的视觉质量,但它会引入影响度量可靠性的表面伪影。摄影测量无法完全重建物体。该研究强调,视觉质量并不能确保几何准确性,而几何准确性对于测量应用至关重要。在这项工作中,与真实情况的比较证实,尽管计算需求较高,但2DGS在准确性和外观之间提供了最佳平衡。这些发现建议将实验扩展到其他具有透明物体(可能还有反射物体)的图像集。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/bd2d/12300396/b3bf4b6ee21c/sensors-25-04410-g011.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/bd2d/12300396/ca1e2a7de029/sensors-25-04410-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/bd2d/12300396/a9b5d87c9d7a/sensors-25-04410-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/bd2d/12300396/fd9ff78c93a1/sensors-25-04410-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/bd2d/12300396/ab4bada751a9/sensors-25-04410-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/bd2d/12300396/631bf1e4262c/sensors-25-04410-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/bd2d/12300396/c958f4e8e644/sensors-25-04410-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/bd2d/12300396/972b904b37dd/sensors-25-04410-g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/bd2d/12300396/3db76a84113a/sensors-25-04410-g008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/bd2d/12300396/1b3ec0507903/sensors-25-04410-g009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/bd2d/12300396/93e89d4d1a36/sensors-25-04410-g010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/bd2d/12300396/b3bf4b6ee21c/sensors-25-04410-g011.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/bd2d/12300396/ca1e2a7de029/sensors-25-04410-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/bd2d/12300396/a9b5d87c9d7a/sensors-25-04410-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/bd2d/12300396/fd9ff78c93a1/sensors-25-04410-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/bd2d/12300396/ab4bada751a9/sensors-25-04410-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/bd2d/12300396/631bf1e4262c/sensors-25-04410-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/bd2d/12300396/c958f4e8e644/sensors-25-04410-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/bd2d/12300396/972b904b37dd/sensors-25-04410-g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/bd2d/12300396/3db76a84113a/sensors-25-04410-g008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/bd2d/12300396/1b3ec0507903/sensors-25-04410-g009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/bd2d/12300396/93e89d4d1a36/sensors-25-04410-g010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/bd2d/12300396/b3bf4b6ee21c/sensors-25-04410-g011.jpg

相似文献

1
Metric Error Assessment Regarding Geometric 3D Reconstruction of Transparent Surfaces via SfM Enhanced by 2D and 3D Gaussian Splatting.关于通过二维和三维高斯点云渲染增强的结构光运动法对透明表面进行几何三维重建的度量误差评估
Sensors (Basel). 2025 Jul 15;25(14):4410. doi: 10.3390/s25144410.
2
PGSR: Planar-Based Gaussian Splatting for Efficient and High-Fidelity Surface Reconstruction.PGSR:基于平面的高斯点云绘制,用于高效且高保真的曲面重建。
IEEE Trans Vis Comput Graph. 2025 Sep;31(9):6100-6111. doi: 10.1109/TVCG.2024.3494046.
3
Systemic Inflammatory Response Syndrome全身炎症反应综合征
4
Three-dimensional saline infusion sonography compared to two-dimensional saline infusion sonography for the diagnosis of focal intracavitary lesions.三维盐水灌注超声与二维盐水灌注超声在诊断腔内局灶性病变中的比较。
Cochrane Database Syst Rev. 2017 May 5;5(5):CD011126. doi: 10.1002/14651858.CD011126.pub2.
5
Systemic pharmacological treatments for chronic plaque psoriasis: a network meta-analysis.慢性斑块状银屑病的全身药理学治疗:一项网状荟萃分析。
Cochrane Database Syst Rev. 2017 Dec 22;12(12):CD011535. doi: 10.1002/14651858.CD011535.pub2.
6
[Volume and health outcomes: evidence from systematic reviews and from evaluation of Italian hospital data].[容量与健康结果:来自系统评价和意大利医院数据评估的证据]
Epidemiol Prev. 2013 Mar-Jun;37(2-3 Suppl 2):1-100.
7
A ROS-Based Online System for 3D Gaussian Splatting Optimization: Flexible Frontend Integration and Real-Time Refinement.一种基于ROS的用于3D高斯点云优化的在线系统:灵活的前端集成与实时优化
Sensors (Basel). 2025 Jul 3;25(13):4151. doi: 10.3390/s25134151.
8
Antidepressants for pain management in adults with chronic pain: a network meta-analysis.抗抑郁药治疗成人慢性疼痛的疼痛管理:一项网络荟萃分析。
Health Technol Assess. 2024 Oct;28(62):1-155. doi: 10.3310/MKRT2948.
9
Sexual Harassment and Prevention Training性骚扰与预防培训
10
Trends and Techniques in 3D Reconstruction and Rendering: A Survey with Emphasis on Gaussian Splatting.三维重建与渲染的趋势和技术:以高斯点渲染为重点的综述
Sensors (Basel). 2025 Jun 9;25(12):3626. doi: 10.3390/s25123626.

本文引用的文献

1
H-BIM and Artificial Intelligence: Classification of Architectural Heritage for Semi-Automatic Scan-to-BIM Reconstruction.H-BIM 与人工智能:建筑遗产的半自动扫描到 BIM 重建分类。
Sensors (Basel). 2023 Feb 23;23(5):2497. doi: 10.3390/s23052497.
2
Surface Reconstruction Assessment in Photogrammetric Applications.摄影测量应用中的表面重建评估。
Sensors (Basel). 2020 Oct 16;20(20):5863. doi: 10.3390/s20205863.
3
Image quality assessment: from error visibility to structural similarity.图像质量评估:从误差可见性到结构相似性。
IEEE Trans Image Process. 2004 Apr;13(4):600-12. doi: 10.1109/tip.2003.819861.