用表面信号参数化学习神经隐式表示

Q4 Computer Science
Yanran Guan, Andrei Chubarau, Ruby Rao, D. Nowrouzezahrai
{"title":"用表面信号参数化学习神经隐式表示","authors":"Yanran Guan, Andrei Chubarau, Ruby Rao, D. Nowrouzezahrai","doi":"10.48550/arXiv.2211.00519","DOIUrl":null,"url":null,"abstract":"Neural implicit surface representations have recently emerged as popular alternative to explicit 3D object encodings, such as polygonal meshes, tabulated points, or voxels. While significant work has improved the geometric fidelity of these representations, much less attention is given to their final appearance. Traditional explicit object representations commonly couple the 3D shape data with auxiliary surface-mapped image data, such as diffuse color textures and fine-scale geometric details in normal maps that typically require a mapping of the 3D surface onto a plane, i.e., a surface parameterization; implicit representations, on the other hand, cannot be easily textured due to lack of configurable surface parameterization. Inspired by this digital content authoring methodology, we design a neural network architecture that implicitly encodes the underlying surface parameterization suitable for appearance data. As such, our model remains compatible with existing mesh-based digital content with appearance data. Motivated by recent work that overfits compact networks to individual 3D objects, we present a new weight-encoded neural implicit representation that extends the capability of neural implicit surfaces to enable various common and important applications of texture mapping. Our method outperforms reasonable baselines and state-of-the-art alternatives.","PeriodicalId":51003,"journal":{"name":"Computer Graphics World","volume":"39 1","pages":"257-264"},"PeriodicalIF":0.0000,"publicationDate":"2022-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":"{\"title\":\"Learning Neural Implicit Representations with Surface Signal Parameterizations\",\"authors\":\"Yanran Guan, Andrei Chubarau, Ruby Rao, D. Nowrouzezahrai\",\"doi\":\"10.48550/arXiv.2211.00519\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Neural implicit surface representations have recently emerged as popular alternative to explicit 3D object encodings, such as polygonal meshes, tabulated points, or voxels. While significant work has improved the geometric fidelity of these representations, much less attention is given to their final appearance. Traditional explicit object representations commonly couple the 3D shape data with auxiliary surface-mapped image data, such as diffuse color textures and fine-scale geometric details in normal maps that typically require a mapping of the 3D surface onto a plane, i.e., a surface parameterization; implicit representations, on the other hand, cannot be easily textured due to lack of configurable surface parameterization. Inspired by this digital content authoring methodology, we design a neural network architecture that implicitly encodes the underlying surface parameterization suitable for appearance data. As such, our model remains compatible with existing mesh-based digital content with appearance data. Motivated by recent work that overfits compact networks to individual 3D objects, we present a new weight-encoded neural implicit representation that extends the capability of neural implicit surfaces to enable various common and important applications of texture mapping. Our method outperforms reasonable baselines and state-of-the-art alternatives.\",\"PeriodicalId\":51003,\"journal\":{\"name\":\"Computer Graphics World\",\"volume\":\"39 1\",\"pages\":\"257-264\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2022-11-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"2\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Computer Graphics World\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.48550/arXiv.2211.00519\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q4\",\"JCRName\":\"Computer Science\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Computer Graphics World","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.48550/arXiv.2211.00519","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"Computer Science","Score":null,"Total":0}
引用次数: 2

摘要

神经隐式表面表示最近作为显式3D对象编码(如多边形网格、表格点或体素)的流行替代方案出现。虽然重要的工作已经提高了这些表示的几何保真度,但对它们最终外观的关注要少得多。传统的显式对象表示通常将3D形状数据与辅助的表面映射图像数据相耦合,例如漫射颜色纹理和法线映射中的精细几何细节,这些数据通常需要将3D表面映射到平面上,即表面参数化;另一方面,由于缺乏可配置的表面参数化,隐式表示不能容易地纹理化。受这种数字内容创作方法的启发,我们设计了一种神经网络架构,该架构可以隐式地对适合于外观数据的底层表面参数化进行编码。因此,我们的模型与现有的基于网格的数字内容和外观数据保持兼容。受最近将紧凑网络过度拟合到单个3D对象的工作的启发,我们提出了一种新的权重编码神经隐式表示,该表示扩展了神经隐式表面的能力,以实现各种常见和重要的纹理映射应用。我们的方法优于合理的基线和最先进的替代方法。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Learning Neural Implicit Representations with Surface Signal Parameterizations
Neural implicit surface representations have recently emerged as popular alternative to explicit 3D object encodings, such as polygonal meshes, tabulated points, or voxels. While significant work has improved the geometric fidelity of these representations, much less attention is given to their final appearance. Traditional explicit object representations commonly couple the 3D shape data with auxiliary surface-mapped image data, such as diffuse color textures and fine-scale geometric details in normal maps that typically require a mapping of the 3D surface onto a plane, i.e., a surface parameterization; implicit representations, on the other hand, cannot be easily textured due to lack of configurable surface parameterization. Inspired by this digital content authoring methodology, we design a neural network architecture that implicitly encodes the underlying surface parameterization suitable for appearance data. As such, our model remains compatible with existing mesh-based digital content with appearance data. Motivated by recent work that overfits compact networks to individual 3D objects, we present a new weight-encoded neural implicit representation that extends the capability of neural implicit surfaces to enable various common and important applications of texture mapping. Our method outperforms reasonable baselines and state-of-the-art alternatives.
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
Computer Graphics World
Computer Graphics World 工程技术-计算机:软件工程
CiteScore
0.03
自引率
0.00%
发文量
0
审稿时长
>12 weeks
×
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:481959085
Book学术官方微信