• 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

基于扩散模型的相移轮廓术对透明物体的重建

Reconstruction of transparent objects using phase shifting profilometry based on diffusion models.

作者信息

Zhang Qinghui, Liu Feng, Lu Lei, Su Zhilong, Pan Wei, Dai Xiangjun

出版信息

Opt Express. 2024 Apr 8;32(8):13342-13356. doi: 10.1364/OE.520937.

DOI:10.1364/OE.520937
PMID:38859307
Abstract

Phase shifting profilometry is an important technique for reconstructing the three-dimensional (3D) geometry of objects with purely diffuse surfaces. However, it is challenging to measure the transparent objects due to the pattern aliasing caused by light refraction and multiple reflections inside the object. In this work, we analyze the aliasing fringe pattern formation for transparent objects and then, propose to learn the front surface light intensity distribution based on the formation principle by using the diffusion models for generating the non-aliased fringe patterns reflected from the front surface only. With the generated fringe patterns, the 3D shape of the transparent objects can be reconstructed via the conventional structured light. We show the feasibility and performance of the proposed method on the data of purely transparent objects that are not seen in the training stage. Moreover, we found it could be generalized to other cases with local-transparent and translucent objects, showing the potential capability of the diffusion based learnable framework in tackling the problems of transparent object reconstruction.

摘要

相移轮廓术是一种用于重建具有纯漫反射表面物体的三维(3D)几何形状的重要技术。然而,由于物体内部光折射和多次反射引起的图案混叠,测量透明物体具有挑战性。在这项工作中,我们分析了透明物体的混叠条纹图案形成,然后,基于形成原理,提出通过使用扩散模型来学习仅从前表面反射的无混叠条纹图案,从而学习前表面光强分布。利用生成的条纹图案,可以通过传统的结构光重建透明物体的3D形状。我们在训练阶段未见过的纯透明物体数据上展示了所提方法的可行性和性能。此外,我们发现它可以推广到其他具有局部透明和半透明物体的情况,显示了基于扩散的可学习框架在解决透明物体重建问题方面的潜在能力。

相似文献

1
Reconstruction of transparent objects using phase shifting profilometry based on diffusion models.基于扩散模型的相移轮廓术对透明物体的重建
Opt Express. 2024 Apr 8;32(8):13342-13356. doi: 10.1364/OE.520937.
2
Spatial phase-shifting profilometry by use of polarization for measuring 3D shapes of metal objects.利用偏振进行空间相移轮廓术以测量金属物体的三维形状。
Opt Express. 2021 Jun 21;29(13):20981-20994. doi: 10.1364/OE.427407.
3
Determining Surface Shape of Translucent Objects with the Combination of Laser-Beam-Based Structured Light and Polarization Technique.基于激光束的结构光与偏振技术相结合测定半透明物体的表面形状
Sensors (Basel). 2021 Oct 1;21(19):6587. doi: 10.3390/s21196587.
4
3D surface reconstruction of small height object based on thin structured light scanning.基于结构光扫描的小高度物体三维表面重建。
Micron. 2021 Apr;143:103022. doi: 10.1016/j.micron.2021.103022. Epub 2021 Jan 29.
5
Effective bias removal for fringe projection profilometry using the dual-tree complex wavelet transform.使用双树复小波变换对条纹投影轮廓术进行有效的偏差去除。
Appl Opt. 2012 Aug 20;51(24):5909-16. doi: 10.1364/AO.51.005909.
6
High-accuracy 3D shape measurement of translucent objects by fringe projection profilometry.基于条纹投影轮廓术的半透明物体高精度三维形状测量
Opt Express. 2019 Jun 24;27(13):18421-18434. doi: 10.1364/OE.27.018421.
7
3D surface reconstruction of transparent objects using laser scanning with a four-layers refinement process.基于四层细化处理的激光扫描透明物体三维表面重建
Opt Express. 2022 Mar 14;30(6):8571-8591. doi: 10.1364/OE.449300.
8
Three-dimensional reconstruction from a fringe projection system through a planar transparent medium.基于条纹投影系统通过平面透明介质进行的三维重建。
Opt Express. 2022 Sep 12;30(19):34824-34834. doi: 10.1364/OE.471265.
9
Single-shot detection of 8 unique monochrome fringe patterns representing 4 distinct directions via multispectral fringe projection profilometry.通过多光谱条纹投影轮廓术对代表4个不同方向的8种独特单色条纹图案进行单次检测。
Sci Rep. 2021 May 14;11(1):10367. doi: 10.1038/s41598-021-88136-4.
10
3D Transparent Object Detection and Reconstruction Based on Passive Mode Single-Pixel Imaging.基于被动模式单像素成像的三维透明物体检测与重建
Sensors (Basel). 2020 Jul 29;20(15):4211. doi: 10.3390/s20154211.