Jiajia Xu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Jiajia Xu has a total of 3 co-authors. Here are the top co-authors by number of shared publications:
- Kyungeun Cho
Department of Computer Science and Artificial Intelligence, College of Advanced Convergence Engineering, Dongguk University-Seoul, 30 Pildongro 1-gil, Jung-gu, Seoul 04620, Republic of Korea
1 shared publication - Rui Gao
Department of Multimedia Engineering, Dongguk University, Seoul, Republic of Korea
1 shared publication - Yipeng Chen
Department of Autonomous Things Intelligence, Dongguk University-Seoul, 30, Pildongro-1-gil, Jung-gu, Seoul 04620, Republic of Korea
1 shared publication
Latest Publications
- Open Access
- 26 December 2022
- Published by MDPI AG in Mathematics
- Vol. 11 (1) , 112
Heterogeneous Feature Fusion Module Based on CNN and Transformer for Multiview Stereo Reconstruction
For decades, a vital area of computer vision research has been multiview stereo (MVS), which creates 3D models of a scene using photographs. This study presents an effective MVS network for 3D reconstruction utilizing multiview pictures. Alternative learning-based reconstruction techniques work well, because CNNs (convolutional neural network) can extract only the image’s local features; however, they contain many artifacts. Herein, a transformer and CNN are used to extract the global and local features of the image, respectively. Additionally, hierarchical aggregation and heterogeneous interaction modules were used to improve these features. They are based on the transformer and can extract dense features with 3D consistency and global context that are necessary to provide accurate matching for MVS.
- 26 December 2022
- Published by MDPI AG in Mathematics
- Vol. 11 (1) , 112
Open AccessHeterogeneous Feature Fusion Module Based on CNN and Transformer for Multiview Stereo Reconstruction
For decades, a vital area of computer vision research has been multiview stereo (MVS), which creates 3D models of a scene using photographs. This study presents an effective MVS network for 3D reconstruction utilizing multiview pictures. Alternative learning-based reconstruction techniques work well, because CNNs (convolutional neural network) can extract only the image’s local features; however, they contain many artifacts. Herein, a transformer and CNN are used to extract the global and local features of the image, respectively. Additionally, hierarchical aggregation and heterogeneous interaction modules were used to improve these features. They are based on the transformer and can extract dense features with 3D consistency and global context that are necessary to provide accurate matching for MVS.