CLC number:
On-line Access: 2020-04-17
Received: 2020-02-11
Revision Accepted: 2020-03-23
Crosschecked: 0000-00-00
Cited: 0
Clicked: 499
Cai-xia LIU, De-hui KONG, Shao-fan WANG, Zhi-yong WANG, Jing-hua LI, Bao-cai YIN. Deep 3D reconstruction: methods, data, and challenges[J]. Frontiers of Information Technology & Electronic Engineering, 1998, -1(-1): .
@article{title="Deep 3D reconstruction: methods, data, and challenges",
author="Cai-xia LIU, De-hui KONG, Shao-fan WANG, Zhi-yong WANG, Jing-hua LI, Bao-cai YIN",
journal="Frontiers of Information Technology & Electronic Engineering",
volume="-1",
number="-1",
pages="",
year="1998",
publisher="Zhejiang University Press & Springer",
doi="10.1631/FITEE.2000068"
}
%0 Journal Article
%T Deep 3D reconstruction: methods, data, and challenges
%A Cai-xia LIU
%A De-hui KONG
%A Shao-fan WANG
%A Zhi-yong WANG
%A Jing-hua LI
%A Bao-cai YIN
%J Journal of Zhejiang University SCIENCE C
%V -1
%N -1
%P
%@ 2095-9184
%D 1998
%I Zhejiang University Press & Springer
%DOI 10.1631/FITEE.2000068
TY - JOUR
T1 - Deep 3D reconstruction: methods, data, and challenges
A1 - Cai-xia LIU
A1 - De-hui KONG
A1 - Shao-fan WANG
A1 - Zhi-yong WANG
A1 - Jing-hua LI
A1 - Bao-cai YIN
J0 - Journal of Zhejiang University Science C
VL - -1
IS - -1
SP -
EP -
%@ 2095-9184
Y1 - 1998
PB - Zhejiang University Press & Springer
ER -
DOI - 10.1631/FITEE.2000068
Abstract: Three-dimensional (3D) reconstruction of shapes is an important research topic in the fields of computer
vision, computer graphics, pattern recognition, and virtual reality. Existing 3D reconstruction methods usually
suffer from two bottlenecks: (1) they involve multiple manually designed states, which lead to cumulative errors,
but can hardly learn semantic features of 3D shapes automatically; (2) they heavily depend on the content and the
quality of images, as well as precisely calibrated cameras. As a result, it is difficult to improve the reconstruction
accuracy of those methods. 3D reconstruction methods based on deep learning overcome both of these bottlenecks
by automatically learning semantic features of 3D shapes from low-quality images using deep networks. However,
while these methods have various architectures, in-depth analysis and comparisons of them are unavailable so far.
We present a comprehensive survey of 3D reconstruction methods based on deep learning. First, based on different
deep learning model architectures, we divide 3D reconstruction methods based on deep learning into four types:
recurrent neural network-, deep AutoEncoder-, generative adversarial network-, and convolutional neural networkbased
methods, and analyze the corresponding methodologies carefully. Second, we investigate, in detail, four
representative databases that are commonly used by the above methods in details. Third, we give a comprehensive
comparison of 3D reconstruction methods based on deep learning, which consists of results of different methods with
respect to the same database, the results of each method with respect to different databases, and the robustness of
each method with respect to the number of viewpoints. Finally, we discuss future development of 3D reconstruction
methods based on deep learning.
Open peer comments: Debate/Discuss/Question/Opinion
<1>