Filling holes in 3D scanned model base on 2D image inpainting

Shu-Chin Lin, T. Shih, Hui-Huang Hsu
{"title":"Filling holes in 3D scanned model base on 2D image inpainting","authors":"Shu-Chin Lin, T. Shih, Hui-Huang Hsu","doi":"10.1109/UMEDIA.2017.8074082","DOIUrl":null,"url":null,"abstract":"Nowadays 3D model scanning is widely used for many purpose. Although scanning technique had become much advanced then earliest, users may still obtain damaged model due to unfamiliar with scanning technique, then we need to repair the model by doing hole-filling and surface reconstruction. In this paper we introduce an approach to fill holes in 3D mesh by using 2D Image Inpainting technique. We create image of depth value to represent depth information and image of color to represent color of surfaces, then inpaint those images and use result images to reconstruct holes of model. The advantage of using Image Inpainting is the flexibility of using image inpainting method, we can use different inpainting method for different purpose. We obtain color and depth image by doing 3D projection and find holes in model by doing hole detection, then we inpaint these images and do 2D to 3D transformation of new added pixels back to 3D space. This work can use any inpaint algorithm without modification. In this paper we use both structural inpainting and textural inpainting, structural inpainting is used for reconstructing depth values and textural inpainting is used for reconstructing texture of surface. The results of our experiment proves that our approach is suitable for model that has uncomplicated structure and texture on the surface.","PeriodicalId":440018,"journal":{"name":"2017 10th International Conference on Ubi-media Computing and Workshops (Ubi-Media)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"5","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2017 10th International Conference on Ubi-media Computing and Workshops (Ubi-Media)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/UMEDIA.2017.8074082","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 5

Abstract

Nowadays 3D model scanning is widely used for many purpose. Although scanning technique had become much advanced then earliest, users may still obtain damaged model due to unfamiliar with scanning technique, then we need to repair the model by doing hole-filling and surface reconstruction. In this paper we introduce an approach to fill holes in 3D mesh by using 2D Image Inpainting technique. We create image of depth value to represent depth information and image of color to represent color of surfaces, then inpaint those images and use result images to reconstruct holes of model. The advantage of using Image Inpainting is the flexibility of using image inpainting method, we can use different inpainting method for different purpose. We obtain color and depth image by doing 3D projection and find holes in model by doing hole detection, then we inpaint these images and do 2D to 3D transformation of new added pixels back to 3D space. This work can use any inpaint algorithm without modification. In this paper we use both structural inpainting and textural inpainting, structural inpainting is used for reconstructing depth values and textural inpainting is used for reconstructing texture of surface. The results of our experiment proves that our approach is suitable for model that has uncomplicated structure and texture on the surface.
在二维图像的基础上对三维扫描模型进行补孔
目前,三维模型扫描被广泛应用于许多领域。尽管当时的扫描技术已经非常先进,但由于用户对扫描技术的不熟悉,仍然可能会得到损坏的模型,这时我们需要通过填孔和表面重建来修复模型。本文介绍了一种利用二维图像补绘技术对三维网格进行补孔的方法。我们先用深度值图像来表示深度信息,用颜色图像来表示表面的颜色,然后对这些图像进行上色,利用结果图像来重建模型的孔洞。使用图像补绘的优点是使用图像补绘方法的灵活性,我们可以针对不同的目的使用不同的补绘方法。我们通过3D投影获得颜色和深度图像,通过洞检测找到模型中的洞,然后对这些图像进行油漆,并将新添加的像素进行2D到3D的转换,将其返回到3D空间。这项工作可以使用任何inpaint算法,无需修改。本文采用结构和纹理两种方法,结构和纹理分别用于深度值的重建和表面纹理的重建。实验结果表明,该方法适用于表面结构和纹理不复杂的模型。
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:604180095
Book学术官方微信