Neural inpainting of folded fabrics with interactive editing

IF 2.5 4区 计算机科学 Q2 COMPUTER SCIENCE, SOFTWARE ENGINEERING Computers & Graphics-Uk Pub Date : 2024-07-08 DOI:10.1016/j.cag.2024.103997
Guillaume Gisbert, Raphaëlle Chaine, David Coeurjolly
{"title":"Neural inpainting of folded fabrics with interactive editing","authors":"Guillaume Gisbert,&nbsp;Raphaëlle Chaine,&nbsp;David Coeurjolly","doi":"10.1016/j.cag.2024.103997","DOIUrl":null,"url":null,"abstract":"<div><p>We propose a deep learning approach for inpainting holes in digital models of fabric surfaces. Leveraging the developable nature of fabric surfaces, we flatten the area surrounding the holes with minor distortion and regularly sample it to obtain a discrete 2D map of the 3D embedding, with an indicator mask outlining holes locations. This enables the use of a standard 2D convolutional neural network to inpaint holes given the 3D positioning of the surface. The provided neural architecture includes an attention mechanism to capture long-range relationships on the surface. Finally, we provide <em>ScarfFolds</em>, a database of folded fabrics patches with varying complexity, which is used to train our convolutional network in a supervised manner. We successfully tested our approach on various examples and illustrated that previous 3D deep learning approaches suffer from several issues when applied to fabrics. Also, our method allows the users to interact with the construction of the inpainted surface. The editing is interactive and supports many tools like vertex grabbing, drape twisting or pinching.</p></div>","PeriodicalId":50628,"journal":{"name":"Computers & Graphics-Uk","volume":"122 ","pages":"Article 103997"},"PeriodicalIF":2.5000,"publicationDate":"2024-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Computers & Graphics-Uk","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0097849324001328","RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"COMPUTER SCIENCE, SOFTWARE ENGINEERING","Score":null,"Total":0}
引用次数: 0

Abstract

We propose a deep learning approach for inpainting holes in digital models of fabric surfaces. Leveraging the developable nature of fabric surfaces, we flatten the area surrounding the holes with minor distortion and regularly sample it to obtain a discrete 2D map of the 3D embedding, with an indicator mask outlining holes locations. This enables the use of a standard 2D convolutional neural network to inpaint holes given the 3D positioning of the surface. The provided neural architecture includes an attention mechanism to capture long-range relationships on the surface. Finally, we provide ScarfFolds, a database of folded fabrics patches with varying complexity, which is used to train our convolutional network in a supervised manner. We successfully tested our approach on various examples and illustrated that previous 3D deep learning approaches suffer from several issues when applied to fabrics. Also, our method allows the users to interact with the construction of the inpainted surface. The editing is interactive and supports many tools like vertex grabbing, drape twisting or pinching.

Abstract Image

查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
通过交互式编辑对折叠织物进行神经绘制
我们提出了一种深度学习方法,用于对织物表面数字模型中的孔洞进行内绘。利用织物表面的可开发性,我们对孔洞周围的区域进行了轻微变形,并对其进行定期采样,以获得三维嵌入的离散二维地图,并用指示掩膜勾勒出孔洞位置。这样就可以使用标准的二维卷积神经网络,根据表面的三维定位来绘制孔洞。所提供的神经架构包括一种注意力机制,用于捕捉表面上的长程关系。最后,我们提供了 ScarfFolds 数据库,这是一个具有不同复杂度的折叠织物补丁数据库,用于以监督方式训练我们的卷积网络。我们成功地在各种示例上测试了我们的方法,并说明了之前的三维深度学习方法在应用于织物时存在一些问题。此外,我们的方法还允许用户与上色表面的构造进行交互。编辑是交互式的,支持许多工具,如抓取顶点、扭曲或捏合。
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 去求助
来源期刊
Computers & Graphics-Uk
Computers & Graphics-Uk 工程技术-计算机:软件工程
CiteScore
5.30
自引率
12.00%
发文量
173
审稿时长
38 days
期刊介绍: Computers & Graphics is dedicated to disseminate information on research and applications of computer graphics (CG) techniques. The journal encourages articles on: 1. Research and applications of interactive computer graphics. We are particularly interested in novel interaction techniques and applications of CG to problem domains. 2. State-of-the-art papers on late-breaking, cutting-edge research on CG. 3. Information on innovative uses of graphics principles and technologies. 4. Tutorial papers on both teaching CG principles and innovative uses of CG in education.
期刊最新文献
Enhancing Visual Analytics systems with guidance: A task-driven methodology Learning geometric complexes for 3D shape classification RenalViz: Visual analysis of cohorts with chronic kidney disease Enhancing semantic mapping in text-to-image diffusion via Gather-and-Bind CGLight: An effective indoor illumination estimation method based on improved convmixer and GauGAN
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1