学习如何从全局图像统计绘制

Anat Levin, A. Zomet, Yair Weiss
{"title":"学习如何从全局图像统计绘制","authors":"Anat Levin, A. Zomet, Yair Weiss","doi":"10.1109/ICCV.2003.1238360","DOIUrl":null,"url":null,"abstract":"Inpainting is the problem of filling-in holes in images. Considerable progress has been made by techniques that use the immediate boundary of the hole and some prior information on images to solve this problem. These algorithms successfully solve the local inpainting problem but they must, by definition, give the same completion to any two holes that have the same boundary, even when the rest of the image is vastly different. We address a different, more global inpainting problem. How can we use the rest of the image in order to learn how to inpaint? We approach this problem from the context of statistical learning. Given a training image we build an exponential family distribution over images that is based on the histograms of local features. We then use this image specific distribution to inpaint the hole by finding the most probable image given the boundary and the distribution. The optimization is done using loopy belief propagation. We show that our method can successfully complete holes while taking into account the specific image statistics. In particular it can give vastly different completions even when the local neighborhoods are identical.","PeriodicalId":131580,"journal":{"name":"Proceedings Ninth IEEE International Conference on Computer Vision","volume":"116 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2003-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"354","resultStr":"{\"title\":\"Learning how to inpaint from global image statistics\",\"authors\":\"Anat Levin, A. Zomet, Yair Weiss\",\"doi\":\"10.1109/ICCV.2003.1238360\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Inpainting is the problem of filling-in holes in images. Considerable progress has been made by techniques that use the immediate boundary of the hole and some prior information on images to solve this problem. These algorithms successfully solve the local inpainting problem but they must, by definition, give the same completion to any two holes that have the same boundary, even when the rest of the image is vastly different. We address a different, more global inpainting problem. How can we use the rest of the image in order to learn how to inpaint? We approach this problem from the context of statistical learning. Given a training image we build an exponential family distribution over images that is based on the histograms of local features. We then use this image specific distribution to inpaint the hole by finding the most probable image given the boundary and the distribution. The optimization is done using loopy belief propagation. We show that our method can successfully complete holes while taking into account the specific image statistics. In particular it can give vastly different completions even when the local neighborhoods are identical.\",\"PeriodicalId\":131580,\"journal\":{\"name\":\"Proceedings Ninth IEEE International Conference on Computer Vision\",\"volume\":\"116 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2003-10-13\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"354\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proceedings Ninth IEEE International Conference on Computer Vision\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICCV.2003.1238360\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings Ninth IEEE International Conference on Computer Vision","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICCV.2003.1238360","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 354

摘要

补图是在图像上补洞的问题。利用孔的直接边界和图像上的一些先验信息来解决这一问题的技术已经取得了相当大的进展。这些算法成功地解决了局部补全问题,但根据定义,它们必须对具有相同边界的任意两个孔给予相同的补全,即使图像的其余部分差异很大。我们解决了一个不同的,更全球性的油漆问题。我们如何使用图像的其余部分来学习如何上色?我们从统计学习的角度来解决这个问题。给定一个训练图像,我们在基于局部特征直方图的图像上建立一个指数族分布。然后,我们使用这个图像特定的分布,通过找到给定边界和分布的最可能的图像来绘制洞。采用循环信念传播方法进行优化。结果表明,该方法可以在考虑特定图像统计量的情况下成功地补全孔洞。特别是,即使当地社区是相同的,它也可以给出截然不同的完成度。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
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
Learning how to inpaint from global image statistics
Inpainting is the problem of filling-in holes in images. Considerable progress has been made by techniques that use the immediate boundary of the hole and some prior information on images to solve this problem. These algorithms successfully solve the local inpainting problem but they must, by definition, give the same completion to any two holes that have the same boundary, even when the rest of the image is vastly different. We address a different, more global inpainting problem. How can we use the rest of the image in order to learn how to inpaint? We approach this problem from the context of statistical learning. Given a training image we build an exponential family distribution over images that is based on the histograms of local features. We then use this image specific distribution to inpaint the hole by finding the most probable image given the boundary and the distribution. The optimization is done using loopy belief propagation. We show that our method can successfully complete holes while taking into account the specific image statistics. In particular it can give vastly different completions even when the local neighborhoods are identical.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Fusion of static and dynamic body biometrics for gait recognition Selection of scale-invariant parts for object class recognition Information theoretic focal length selection for real-time active 3D object tracking A multi-scale generative model for animate shapes and parts Integrated edge and junction detection with the boundary tensor
×
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