基于草图的流形正则化建模

Juncheng Liu, Z. Lian, J. Feng, Bingfeng Zhou
{"title":"基于草图的流形正则化建模","authors":"Juncheng Liu, Z. Lian, J. Feng, Bingfeng Zhou","doi":"10.1145/2820903.2820906","DOIUrl":null,"url":null,"abstract":"This paper proposes a novel method to automatically generate the realistic 3D model for a 2D free-hand sketch drawn by a user. Specifically, the proposed method first retrieves 3D shapes based on the sketch, and then implements a deformation procedure to make the most similar model retrieved more consistent with the provided sketch. In the retrieval stage, a locality preserving view selection scheme is adopted to generate views that are well-suited to create sketch images for the 3D object. Our method predicates the sketch views accurately while significantly reduces the amount of rendering views. In the deformation stage, retrieved models are modified according to the input sketches. Since free-hand sketches always contain various kinds of drawing errors such as stroke jittering and asymmetry, extracting plausible deforming information from sketches while discarding undesirable drawing errors is difficult. To address these issues, we obtain the plausible deformation for the corresponding sketch by exploring a shape manifold trained on a collection of similar 3D models. Experimental results show that the proposed method can generate 3D shapes that correspond quite well with 2D sketches.","PeriodicalId":21720,"journal":{"name":"SIGGRAPH Asia 2015 Technical Briefs","volume":"13 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2015-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"Sketch based modeling via manifold regularization\",\"authors\":\"Juncheng Liu, Z. Lian, J. Feng, Bingfeng Zhou\",\"doi\":\"10.1145/2820903.2820906\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This paper proposes a novel method to automatically generate the realistic 3D model for a 2D free-hand sketch drawn by a user. Specifically, the proposed method first retrieves 3D shapes based on the sketch, and then implements a deformation procedure to make the most similar model retrieved more consistent with the provided sketch. In the retrieval stage, a locality preserving view selection scheme is adopted to generate views that are well-suited to create sketch images for the 3D object. Our method predicates the sketch views accurately while significantly reduces the amount of rendering views. In the deformation stage, retrieved models are modified according to the input sketches. Since free-hand sketches always contain various kinds of drawing errors such as stroke jittering and asymmetry, extracting plausible deforming information from sketches while discarding undesirable drawing errors is difficult. To address these issues, we obtain the plausible deformation for the corresponding sketch by exploring a shape manifold trained on a collection of similar 3D models. Experimental results show that the proposed method can generate 3D shapes that correspond quite well with 2D sketches.\",\"PeriodicalId\":21720,\"journal\":{\"name\":\"SIGGRAPH Asia 2015 Technical Briefs\",\"volume\":\"13 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2015-11-02\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"SIGGRAPH Asia 2015 Technical Briefs\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1145/2820903.2820906\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"SIGGRAPH Asia 2015 Technical Briefs","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/2820903.2820906","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1

摘要

本文提出了一种针对用户手绘的二维草图自动生成逼真的三维模型的新方法。具体而言,该方法首先基于草图检索三维形状,然后实现变形过程,使检索到的最相似的模型与提供的草图更一致。在检索阶段,采用局域保持视图选择方案,生成适合创建三维物体草图的视图。我们的方法准确地预测了草图视图,同时显著减少了渲染视图的数量。在变形阶段,根据输入的草图对检索到的模型进行修正。由于手绘草图总是包含各种绘制误差,如笔画抖动和不对称,从草图中提取合理的变形信息,同时丢弃不希望的绘制误差是困难的。为了解决这些问题,我们通过探索在类似3D模型集合上训练的形状流形来获得相应草图的合理变形。实验结果表明,该方法能较好地生成与二维草图对应的三维形状。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Sketch based modeling via manifold regularization
This paper proposes a novel method to automatically generate the realistic 3D model for a 2D free-hand sketch drawn by a user. Specifically, the proposed method first retrieves 3D shapes based on the sketch, and then implements a deformation procedure to make the most similar model retrieved more consistent with the provided sketch. In the retrieval stage, a locality preserving view selection scheme is adopted to generate views that are well-suited to create sketch images for the 3D object. Our method predicates the sketch views accurately while significantly reduces the amount of rendering views. In the deformation stage, retrieved models are modified according to the input sketches. Since free-hand sketches always contain various kinds of drawing errors such as stroke jittering and asymmetry, extracting plausible deforming information from sketches while discarding undesirable drawing errors is difficult. To address these issues, we obtain the plausible deformation for the corresponding sketch by exploring a shape manifold trained on a collection of similar 3D models. Experimental results show that the proposed method can generate 3D shapes that correspond quite well with 2D sketches.
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
×
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