.png){kind=icon}
.png){kind=icon}
Return
FinerPCN: High fidelity point cloud completion network using pointwise convolution
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neucom.2021.06.080.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
3D scanners often obtain partial point clouds due to occlusion and limitation of viewing angles. Point cloud completion aims at inferring the full shape of an object from an incomplete point set. Existing deep learning models either do not consider local information or easily degrade the sharp details of the input, thereby losing some existing structures. In this paper, we propose a high fidelity point cloud completion network using pointwise convolution, called FinerPCN. FinerPCN generates complete and fine point clouds in a coarse-to-fine manner. FinerPCN consists of two subnetworks: an encoder-decoder for gener-ating a coarse shape and pointwise convolution for refining its local structure. By repeatedly feeding par-tial input into the second subnetwork, FinerPCN effectively considers local information and alleviates structural blur of input while maintaining global shape. Experimental results show that FinerPCN gener-ates finer detailed completion results than state-of-the-art methods while successfully keeping the shape of the input. (c) 2021 Published by Elsevier B.V.
Keywords:
3D point cloud
Shape completion
Point analysis
Deep learning
Point completion network
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.