Real-Time Mesh Extraction from Implicit Functions via Direct Reconstruction of Decision Boundary

Wataru Kawai, Yusuke Mukuta, T. Harada
{"title":"Real-Time Mesh Extraction from Implicit Functions via Direct Reconstruction of Decision Boundary","authors":"Wataru Kawai, Yusuke Mukuta, T. Harada","doi":"10.1109/ICRA48506.2021.9560749","DOIUrl":null,"url":null,"abstract":"The ability to estimate 3D object shape from a single image is vital to robotics and manufacturing. For instance, it enables iterative trial-and-error in simulated environments. In single-view reconstruction, implicit functions have demonstrated superior results over traditional methods. However, implicit functions suffer from the heavy computation of mesh extraction. This is due to the indirect mesh extraction, where the number of evaluation points grows cubically with resolution. On the other hand, reducing the resolution results in the discretization error of marching cubes (MC). In this work, we aim to perform efficient and accurate mesh extraction from implicit functions. The idea is to directly reconstruct the decision boundary of implicit functions as a mesh by reverse tracing from the output. It eliminates the need for evaluating massive points and error-prone MC. Consequently, we propose implementing an implicit function via a composite function of a flow and Binary-coded Input Neural Network (BCINN). The boundary of BCINN is easily identifiable, and the flow is invertible. Owing to these properties, the decision boundary of the composite function can be directly and efficiently reconstructed. In our experiments, we demonstrate that the proposed method significantly improves runtime/memory efficiency, with results comparable to those of existing methods. Specifically, our method enables real-time high-quality mesh inference from a single image.","PeriodicalId":108312,"journal":{"name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","volume":"59 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2021 IEEE International Conference on Robotics and Automation (ICRA)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICRA48506.2021.9560749","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

The ability to estimate 3D object shape from a single image is vital to robotics and manufacturing. For instance, it enables iterative trial-and-error in simulated environments. In single-view reconstruction, implicit functions have demonstrated superior results over traditional methods. However, implicit functions suffer from the heavy computation of mesh extraction. This is due to the indirect mesh extraction, where the number of evaluation points grows cubically with resolution. On the other hand, reducing the resolution results in the discretization error of marching cubes (MC). In this work, we aim to perform efficient and accurate mesh extraction from implicit functions. The idea is to directly reconstruct the decision boundary of implicit functions as a mesh by reverse tracing from the output. It eliminates the need for evaluating massive points and error-prone MC. Consequently, we propose implementing an implicit function via a composite function of a flow and Binary-coded Input Neural Network (BCINN). The boundary of BCINN is easily identifiable, and the flow is invertible. Owing to these properties, the decision boundary of the composite function can be directly and efficiently reconstructed. In our experiments, we demonstrate that the proposed method significantly improves runtime/memory efficiency, with results comparable to those of existing methods. Specifically, our method enables real-time high-quality mesh inference from a single image.
基于直接重构决策边界的隐函数实时网格提取
从单个图像中估计3D物体形状的能力对机器人和制造业至关重要。例如,它可以在模拟环境中进行反复的试错。在单视图重建中,隐式函数显示出优于传统方法的效果。然而,隐式函数的网格提取计算量较大。这是由于间接网格提取,其中评估点的数量随着分辨率呈立方增长。另一方面,分辨率的降低会导致行进立方体的离散化误差。在这项工作中,我们的目标是从隐式函数中进行高效准确的网格提取。其思想是通过从输出反向跟踪,直接将隐函数的决策边界重构为网格。它消除了评估大量点和容易出错的MC的需要。因此,我们建议通过流和二进制编码输入神经网络(BCINN)的复合函数实现隐式函数。BCINN边界易于识别,且流是可逆的。由于这些性质,可以直接有效地重建复合函数的决策边界。在我们的实验中,我们证明了该方法显著提高了运行时/内存效率,其结果与现有方法相当。具体来说,我们的方法可以从单个图像中进行实时高质量的网格推断。
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