Learning modified indicator functions for surface reconstruction
Learning modified indicator functions for surface reconstruction
复制标题
学习用于表面重建的修正指示函数
DOI：
10.1016/j.cag.2021.10.017
复制
发表时间：
2022-02-25
影响因子：
2.5
通讯作者：
Wang, Bin
中科院分区：
文献类型：
--
作者：
Xiao, Dong;Lin, Siyou;Wang, Bin
曲面重建是三维图形学中的一个基本问题。在本文中，我们提出了一种基于学习的方法隐式曲面重建的原始点云没有法线。我们的方法受到势能理论中高斯引理的启发，给出了指示函数的显式积分公式。我们设计了一种新的深度神经网络来执行表面积分，并从无方向和有噪声的点云中学习修改后的指示函数。我们将具有不同尺度的特征连接起来，以获得对积分的精确逐点贡献。此外，我们提出了一种新的表面元素特征提取器学习局部形状属性。实验结果表明，该方法能够从不同噪声尺度的点云生成具有高法向一致性的光滑曲面，与现有的数据驱动和非数据驱动方法相比，具有最佳的重构性能。(c)2021爱思唯尔有限公司保留所有权利。
Surface reconstruction is a fundamental problem in 3D graphics. In this paper, we propose a learning based approach for implicit surface reconstruction from raw point clouds without normals. Our method is inspired by Gauss Lemma in potential energy theory, which gives an explicit integral formula for the indicator functions. We design a novel deep neural network to perform surface integral and learn the modified indicator functions from un-oriented and noisy point clouds. We concatenate features with different scales for accurate point-wise contributions to the integral. Moreover, we propose a novel Surface Element Feature Extractor to learn local shape properties. Experiments show that our method generates smooth surfaces with high normal consistency from point clouds with different noise scales and achieves state-of-the-art reconstruction performance compared with current data-driven and non-data-driven approaches. (c) 2021 Elsevier Ltd. All rights reserved.