IEICE TRANSACTIONS on Information
Learning Multi-Level Features for Improved 3D Reconstruction
Summary :
3D reconstruction methods using neural networks are popular and have been studied extensively. However, the resulting models typically lack detail, reducing the quality of the 3D reconstruction. This is because the network is not designed to capture the fine details of the object. Therefore, in this paper, we propose two networks designed to capture both the coarse and fine details of the object to improve the reconstruction of the detailed parts of the object. To accomplish this, we design two networks. The first network uses a multi-scale architecture with skip connections to associate and merge features from other levels. For the second network, we design a multi-branch deep generative network that separately learns the local features, generic features, and the intermediate features through three different tailored components. In both network architectures, the principle entails allowing the network to learn features at different levels that can reconstruct the fine parts and the overall shape of the reconstructed 3D model. We show that both of our methods outperformed state-of-the-art approaches.
- Publication
- IEICE TRANSACTIONS on Information Vol.E106-D No.3 pp.381-390
- Publication Date
- 2023/03/01
- Publicized
- 2022/12/08
- Online ISSN
- 1745-1361
- DOI
- 10.1587/transinf.2020ZDP7508
- Type of Manuscript
- PAPER
- Category
- Image Recognition, Computer Vision
Authors
Fairuz SAFWAN MAHAD
Osaka Prefecture University
Masakazu IWAMURA
Osaka Prefecture University
Koichi KISE
Osaka Prefecture University
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Fairuz SAFWAN MAHAD, Masakazu IWAMURA, Koichi KISE, "Learning Multi-Level Features for Improved 3D Reconstruction" in IEICE TRANSACTIONS on Information,
vol. E106-D, no. 3, pp. 381-390, March 2023, doi: 10.1587/transinf.2020ZDP7508.
Abstract: 3D reconstruction methods using neural networks are popular and have been studied extensively. However, the resulting models typically lack detail, reducing the quality of the 3D reconstruction. This is because the network is not designed to capture the fine details of the object. Therefore, in this paper, we propose two networks designed to capture both the coarse and fine details of the object to improve the reconstruction of the detailed parts of the object. To accomplish this, we design two networks. The first network uses a multi-scale architecture with skip connections to associate and merge features from other levels. For the second network, we design a multi-branch deep generative network that separately learns the local features, generic features, and the intermediate features through three different tailored components. In both network architectures, the principle entails allowing the network to learn features at different levels that can reconstruct the fine parts and the overall shape of the reconstructed 3D model. We show that both of our methods outperformed state-of-the-art approaches.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2020ZDP7508/_p
Copy
@ARTICLE{e106-d_3_381,
author={Fairuz SAFWAN MAHAD, Masakazu IWAMURA, Koichi KISE, },
journal={IEICE TRANSACTIONS on Information},
title={Learning Multi-Level Features for Improved 3D Reconstruction},
year={2023},
volume={E106-D},
number={3},
pages={381-390},
abstract={3D reconstruction methods using neural networks are popular and have been studied extensively. However, the resulting models typically lack detail, reducing the quality of the 3D reconstruction. This is because the network is not designed to capture the fine details of the object. Therefore, in this paper, we propose two networks designed to capture both the coarse and fine details of the object to improve the reconstruction of the detailed parts of the object. To accomplish this, we design two networks. The first network uses a multi-scale architecture with skip connections to associate and merge features from other levels. For the second network, we design a multi-branch deep generative network that separately learns the local features, generic features, and the intermediate features through three different tailored components. In both network architectures, the principle entails allowing the network to learn features at different levels that can reconstruct the fine parts and the overall shape of the reconstructed 3D model. We show that both of our methods outperformed state-of-the-art approaches.},
keywords={},
doi={10.1587/transinf.2020ZDP7508},
ISSN={1745-1361},
month={March},}
Copy
TY - JOUR
TI - Learning Multi-Level Features for Improved 3D Reconstruction
T2 - IEICE TRANSACTIONS on Information
SP - 381
EP - 390
AU - Fairuz SAFWAN MAHAD
AU - Masakazu IWAMURA
AU - Koichi KISE
PY - 2023
DO - 10.1587/transinf.2020ZDP7508
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E106-D
IS - 3
JA - IEICE TRANSACTIONS on Information
Y1 - March 2023
AB - 3D reconstruction methods using neural networks are popular and have been studied extensively. However, the resulting models typically lack detail, reducing the quality of the 3D reconstruction. This is because the network is not designed to capture the fine details of the object. Therefore, in this paper, we propose two networks designed to capture both the coarse and fine details of the object to improve the reconstruction of the detailed parts of the object. To accomplish this, we design two networks. The first network uses a multi-scale architecture with skip connections to associate and merge features from other levels. For the second network, we design a multi-branch deep generative network that separately learns the local features, generic features, and the intermediate features through three different tailored components. In both network architectures, the principle entails allowing the network to learn features at different levels that can reconstruct the fine parts and the overall shape of the reconstructed 3D model. We show that both of our methods outperformed state-of-the-art approaches.
ER -
English
