Learning Pyramidal Feature Hierarchy for 3D Reconstruction

Fairuz Safwan MAHAD; Masakazu IWAMURA; Koichi KISE

doi:10.1587/transinf.2020ZDL0001

Learning Pyramidal Feature Hierarchy for 3D Reconstruction

Fairuz Safwan MAHAD, Masakazu IWAMURA, Koichi KISE

Full Text Views

0

Cite this

Summary :

Neural network-based three-dimensional (3D) reconstruction methods have produced promising results. However, they do not pay particular attention to reconstructing detailed parts of objects. This occurs because the network is not designed to capture the fine details of objects. In this paper, we propose a network designed to capture both the coarse and fine details of objects to improve the reconstruction of the fine parts of objects.

Publication: IEICE TRANSACTIONS on Information Vol.E105-D No.2 pp.446-449

Publication Date: 2022/02/01

Publicized: 2021/11/16

Online ISSN: 1745-1361

DOI: 10.1587/transinf.2020ZDL0001

Type of Manuscript: LETTER

Category: Image Recognition, Computer Vision

Authors

Fairuz Safwan MAHAD
  Osaka Prefecture University
Masakazu IWAMURA
  Osaka Prefecture University
Koichi KISE
  Osaka Prefecture University

Keyword

computer vision, 3D reconstruction, deep learning, multi-view

Cite this

Copy

Fairuz Safwan MAHAD, Masakazu IWAMURA, Koichi KISE, "Learning Pyramidal Feature Hierarchy for 3D Reconstruction" in IEICE TRANSACTIONS on Information, vol. E105-D, no. 2, pp. 446-449, February 2022, doi: 10.1587/transinf.2020ZDL0001.
Abstract: Neural network-based three-dimensional (3D) reconstruction methods have produced promising results. However, they do not pay particular attention to reconstructing detailed parts of objects. This occurs because the network is not designed to capture the fine details of objects. In this paper, we propose a network designed to capture both the coarse and fine details of objects to improve the reconstruction of the fine parts of objects.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2020ZDL0001/_p

Copy

@ARTICLE{e105-d_2_446,
author={Fairuz Safwan MAHAD, Masakazu IWAMURA, Koichi KISE, },
journal={IEICE TRANSACTIONS on Information},
title={Learning Pyramidal Feature Hierarchy for 3D Reconstruction},
year={2022},
volume={E105-D},
number={2},
pages={446-449},
abstract={Neural network-based three-dimensional (3D) reconstruction methods have produced promising results. However, they do not pay particular attention to reconstructing detailed parts of objects. This occurs because the network is not designed to capture the fine details of objects. In this paper, we propose a network designed to capture both the coarse and fine details of objects to improve the reconstruction of the fine parts of objects.},
keywords={},
doi={10.1587/transinf.2020ZDL0001},
ISSN={1745-1361},
month={February},}

Copy

TY - JOUR
TI - Learning Pyramidal Feature Hierarchy for 3D Reconstruction
T2 - IEICE TRANSACTIONS on Information
SP - 446
EP - 449
AU - Fairuz Safwan MAHAD
AU - Masakazu IWAMURA
AU - Koichi KISE
PY - 2022
DO - 10.1587/transinf.2020ZDL0001
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E105-D
IS - 2
JA - IEICE TRANSACTIONS on Information
Y1 - February 2022
AB - Neural network-based three-dimensional (3D) reconstruction methods have produced promising results. However, they do not pay particular attention to reconstructing detailed parts of objects. This occurs because the network is not designed to capture the fine details of objects. In this paper, we propose a network designed to capture both the coarse and fine details of objects to improve the reconstruction of the fine parts of objects.
ER -