3D shape completion using multilayer spherical depth parameters
3D shape completion using multilayer spherical depth parameters
Yükleniyor...
Abstract
3D shape completion plays a crucial role in transforming the distorted real world data to the digital data which represents the original data accurately. In recent times, there has been several works on 3D shape completion with deep learning models. Due to the input requirements of deep learning models, it is necessary to form the input data into a specific format before feeding into the network. In this work, Multilayer Spherical Depth Parameters used with a specific deep learning model for 3D shape completion and its highly accurate results will be presented. © 2021 IEEE.
Description
29th IEEE Conference on Signal Processing and Communications Applications, SIU 2021 -- 9 June 2021 through 11 June 2021 -- 170536
Keywords
Convolutional neural networks, Shape completion, Spherical depth parameters, 3D modeling, Learning systems, Metadata, Multilayers, Signal processing, 3-D shape, Depth parameters, Digital datas, Highly accurate, Input datas, Learning models, Real-world, Deep learning, Signal processing, Metadata, Spherical depth parameters, Learning systems, Deep learning, Highly accurate, Shape completion, Learning models, 3D modeling, 3-D shape, Multilayers, Digital datas, Real-world, Depth parameters, Input datas, Convolutional neural networks
Fields of Science
02 engineering and technology, 0202 electrical engineering, electronic engineering, information engineering
Citation
WoS Q
N/A
Scopus Q
N/A
Source
SIU 2021 - 29th IEEE Conference on Signal Processing and Communications Applications, Proceedings
Volume
Issue
Start Page
1
End Page
4
Yükleniyor...