Improved Multiview Decomposition for Single-Image High-Resolution 3D Object Reconstruction

Joint Authors

Peng, Jiansheng
Fu, Kui
Wei, Qingjin
Qin, Yong
He, Qiwen

Source

Wireless Communications and Mobile Computing

Issue

Vol. 2020, Issue 2020 (31 Dec. 2020), pp.1-14, 14 p.

Publisher

Hindawi Publishing Corporation

Publication Date

2020-12-28

Country of Publication

Egypt

No. of Pages

14

Main Subjects

Information Technology and Computer Science

Abstract EN

As a representative technology of artificial intelligence, 3D reconstruction based on deep learning can be integrated into the edge computing framework to form an intelligent edge and then realize the intelligent processing of the edge.

Recently, high-resolution representation of 3D objects using multiview decomposition (MVD) architecture is a fast reconstruction method for generating objects with realistic details from a single RGB image.

The results of high-resolution 3D object reconstruction are related to two aspects.

On the one hand, a low-resolution reconstruction network represents a good 3D object from a single RGB image.

On the other hand, a high-resolution reconstruction network maximizes fine low-resolution 3D objects.

To improve these two aspects and further enhance the high-resolution reconstruction capabilities of the 3D object generation network, we study and improve the low-resolution 3D generation network and the depth map superresolution network.

Eventually, we get an improved multiview decomposition (IMVD) network.

First, we use a 2D image encoder with multifeature fusion (MFF) to enhance the feature extraction capability of the model.

Second, a 3D decoder using an effective subpixel convolutional neural network (3D ESPCN) improves the decoding speed in the decoding stage.

Moreover, we design a multiresidual dense block (MRDB) to optimize the depth map superresolution network, which allows the model to capture more object details and reduce the model parameters by approximately 25% when the number of network layers is doubled.

The experimental results show that the proposed IMVD is better than the original MVD in the 3D object superresolution experiment and the high-resolution 3D reconstruction experiment of a single image.

American Psychological Association (APA)

Peng, Jiansheng& Fu, Kui& Wei, Qingjin& Qin, Yong& He, Qiwen. 2020. Improved Multiview Decomposition for Single-Image High-Resolution 3D Object Reconstruction. Wireless Communications and Mobile Computing،Vol. 2020, no. 2020, pp.1-14.
https://search.emarefa.net/detail/BIM-1214821

Modern Language Association (MLA)

Peng, Jiansheng…[et al.]. Improved Multiview Decomposition for Single-Image High-Resolution 3D Object Reconstruction. Wireless Communications and Mobile Computing No. 2020 (2020), pp.1-14.
https://search.emarefa.net/detail/BIM-1214821

American Medical Association (AMA)

Peng, Jiansheng& Fu, Kui& Wei, Qingjin& Qin, Yong& He, Qiwen. Improved Multiview Decomposition for Single-Image High-Resolution 3D Object Reconstruction. Wireless Communications and Mobile Computing. 2020. Vol. 2020, no. 2020, pp.1-14.
https://search.emarefa.net/detail/BIM-1214821

Data Type

Journal Articles

Language

English

Notes

Includes bibliographical references

Record ID

BIM-1214821