当前位置:
X-MOL 学术
›
arXiv.cs.CG
›
论文详情
Our official English website, www.x-mol.net, welcomes your
feedback! (Note: you will need to create a separate account there.)
Scalable Surface Reconstruction with Delaunay-Graph Neural Networks
arXiv - CS - Computational Geometry Pub Date : 2021-07-13 , DOI: arxiv-2107.06130 Raphael Sulzer, Loic Landrieu, Renaud Marlet, Bruno Vallet
arXiv - CS - Computational Geometry Pub Date : 2021-07-13 , DOI: arxiv-2107.06130 Raphael Sulzer, Loic Landrieu, Renaud Marlet, Bruno Vallet
We introduce a novel learning-based, visibility-aware, surface reconstruction
method for large-scale, defect-laden point clouds. Our approach can cope with
the scale and variety of point cloud defects encountered in real-life
Multi-View Stereo (MVS) acquisitions. Our method relies on a 3D Delaunay
tetrahedralization whose cells are classified as inside or outside the surface
by a graph neural network and an energy model solvable with a graph cut. Our
model, making use of both local geometric attributes and line-of-sight
visibility information, is able to learn a visibility model from a small amount
of synthetic training data and generalizes to real-life acquisitions. Combining
the efficiency of deep learning methods and the scalability of energy based
models, our approach outperforms both learning and non learning-based
reconstruction algorithms on two publicly available reconstruction benchmarks.
中文翻译:
使用 Delaunay-Graph 神经网络进行可扩展的表面重建
我们介绍了一种新的基于学习的、可见性感知的、用于大规模缺陷点云的表面重建方法。我们的方法可以应对现实生活中多视图立体 (MVS) 采集中遇到的点云缺陷的规模和种类。我们的方法依赖于 3D Delaunay 四面体化,其细胞通过图神经网络和可通过图切割求解的能量模型分类为表面内部或外部。我们的模型利用局部几何属性和视线可见性信息,能够从少量合成训练数据中学习可见性模型,并将其推广到现实生活中。结合深度学习方法的效率和基于能量的模型的可扩展性,
更新日期:2021-07-14
中文翻译:
使用 Delaunay-Graph 神经网络进行可扩展的表面重建
我们介绍了一种新的基于学习的、可见性感知的、用于大规模缺陷点云的表面重建方法。我们的方法可以应对现实生活中多视图立体 (MVS) 采集中遇到的点云缺陷的规模和种类。我们的方法依赖于 3D Delaunay 四面体化,其细胞通过图神经网络和可通过图切割求解的能量模型分类为表面内部或外部。我们的模型利用局部几何属性和视线可见性信息,能够从少量合成训练数据中学习可见性模型,并将其推广到现实生活中。结合深度学习方法的效率和基于能量的模型的可扩展性,