Ziheng Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Ziheng Wang has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Fengqi Zhu
Shandong Provincial Institute of Land Surveying and Mapping, Jinan 250101, China
2 shared publications - Guobiao Yao
School of Surveying and Geo-Informatics, Shandong Jianzhu University, Jinan 250101, China
2 shared publications - Guozhong Wei
Shandong Provincial Institute of Land Surveying and Mapping, Jinan 250101, China
2 shared publications - Qian Yu
Shandong Provincial Institute of Land and Resources Surveying and Mapping, Jinan 250013, China
2 shared publications - Min Wei
Shandong Zhengyuan Aerial Remote Sensing Technology Co., Ltd., China
1 shared publication - Min Wei
Shandong Zhengyuan Aerial Remote Sensing Technology Co., Ltd., Jinan 250101, China
1 shared publication
Latest Publications
- Open Access
- 24 January 2025
- Published by MDPI AG in ISPRS International Journal of Geo-Information
- Vol. 14 (2) , 43
Multi-View Three-Dimensional Reconstruction Based on Feature Enhancement and Weight Optimization Network
Aiming to address the issue that existing multi-view stereo reconstruction methods have insufficient adaptability to the repetitive and weak textures in multi-view images, this paper proposes a three-dimensional (3D) reconstruction algorithm based on Feature Enhancement and Weight Optimization MVSNet (Abbreviated as FEWO-MVSNet). To obtain accurate and detailed global and local features, we first develop an adaptive feature enhancement approach to obtain multi-scale information from the images. Second, we introduce an attention mechanism and a spatial feature capture module to enable high-sensitivity detection for weak texture features. Third, based on the 3D convolutional neural network, the fine depth map for multi-view images can be predicted and the complete 3D model is subsequently reconstructed. Last, we evaluated the proposed FEWO-MVSNet through training and testing on the DTU, BlendedMVS, and Tanks and Temples datasets. The results demonstrate significant superiorities of our method for 3D reconstruction from multi-view images, with our method ranking first in accuracy and second in completeness when compared to the existing representative methods.
- 24 January 2025
- Published by MDPI AG in ISPRS International Journal of Geo-Information
- Vol. 14 (2) , 43
Open AccessMulti-View Three-Dimensional Reconstruction Based on Feature Enhancement and Weight Optimization Network
Aiming to address the issue that existing multi-view stereo reconstruction methods have insufficient adaptability to the repetitive and weak textures in multi-view images, this paper proposes a three-dimensional (3D) reconstruction algorithm based on Feature Enhancement and Weight Optimization MVSNet (Abbreviated as FEWO-MVSNet). To obtain accurate and detailed global and local features, we first develop an adaptive feature enhancement approach to obtain multi-scale information from the images. Second, we introduce an attention mechanism and a spatial feature capture module to enable high-sensitivity detection for weak texture features. Third, based on the 3D convolutional neural network, the fine depth map for multi-view images can be predicted and the complete 3D model is subsequently reconstructed. Last, we evaluated the proposed FEWO-MVSNet through training and testing on the DTU, BlendedMVS, and Tanks and Temples datasets. The results demonstrate significant superiorities of our method for 3D reconstruction from multi-view images, with our method ranking first in accuracy and second in completeness when compared to the existing representative methods.
- Open Access
- 31 October 2024
- Published by MDPI AG in Preprints.org
Multi-View 3D Reconstruction Based on FEWO-MVSNet
Aiming to address the issue that the existing multi-view stereo reconstruction methods have insufficient adaptability to the repetitive patterns and weak textures in the multi-view images, this paper proposes a three-dimensional (3D) reconstruction algorithm based on feature enhancement and weight optimization MVSNet (Abbreviated as FEWO-MVSNet). To obtain accurate and detailed global and local features, we first develop an adaptive feature enhancement approach to obtain multi-scale information from the images. Second, we introduce an attention mechanism and a spatial feature capture module to enable high-sensitivity detection for weak texture features. Third, based on the 3D convolutional neural network, the fine depth map for multi-view images can be predicted and the complete 3D model is subsequently reconstructed. Last, we evaluated the proposed FEWO-MVSNet through training and testing on the DTU, BlendedMVS, and Tanks&Temples datasets. The results demonstrate significant superiorities of our method for 3D reconstruction from multi-view images, with our method ranking first in accuracy and second in completeness when compared to the existing representative methods.
- 31 October 2024
- Published by MDPI AG in Preprints.org
Open AccessMulti-View 3D Reconstruction Based on FEWO-MVSNet
Aiming to address the issue that the existing multi-view stereo reconstruction methods have insufficient adaptability to the repetitive patterns and weak textures in the multi-view images, this paper proposes a three-dimensional (3D) reconstruction algorithm based on feature enhancement and weight optimization MVSNet (Abbreviated as FEWO-MVSNet). To obtain accurate and detailed global and local features, we first develop an adaptive feature enhancement approach to obtain multi-scale information from the images. Second, we introduce an attention mechanism and a spatial feature capture module to enable high-sensitivity detection for weak texture features. Third, based on the 3D convolutional neural network, the fine depth map for multi-view images can be predicted and the complete 3D model is subsequently reconstructed. Last, we evaluated the proposed FEWO-MVSNet through training and testing on the DTU, BlendedMVS, and Tanks&Temples datasets. The results demonstrate significant superiorities of our method for 3D reconstruction from multi-view images, with our method ranking first in accuracy and second in completeness when compared to the existing representative methods.