人工智能
深度学习
计算机视觉
卷积神经网络
超分辨率
残余物
模式识别(心理学)
作者
Rajat Sharma,Tobias Schwandt,Christian Kunert,Steffen Urban,Wolfgang Broll
出处
期刊:arXiv: Computer Vision and Pattern Recognition
日期:2021-01-01
被引量:7
标识
DOI:10.5220/0010211600700079
摘要
The reconstruction of real-world surfaces is on high demand in various applications. Most existing reconstruction approaches apply 3D scanners for creating point clouds which are generally sparse and of low density. These points clouds will be triangulated and used for visualization in combination with surface normals estimated by geometrical approaches. However, the quality of the reconstruction depends on the density of the point cloud and the estimation of the surface normals. In this paper, we present a novel deep learning architecture for point cloud upsampling that enables subsequent stable and smooth surface reconstruction. A noisy point cloud of low density with corresponding point normals is used to estimate a point cloud with higher density and appendant point normals. To this end, we propose a compound loss function that encourages the network to estimate points that lie on a surface including normals accurately predicting the orientation of the surface. Our results show the benefit of estimating normals together with point positions. The resulting point cloud is smoother, more complete, and the final surface reconstruction is much closer to ground truth.
科研通智能强力驱动
Strongly Powered by AbleSci AI