BCA-MVSNet: Integrating BIFPN and CA for Enhanced Detail Texture in Multi-View Stereo Reconstruction

Guardado en:
Detalles Bibliográficos
Publicado en:Electronics vol. 14, no. 15 (2025), p. 2958-2984
Autor principal: Long, Ning
Otros Autores: Duan Zhengxu, Hu, Xiao, Chen Mingju
Publicado:
MDPI AG
Materias:
Acceso en línea:Citation/Abstract
Full Text + Graphics
Full Text - PDF
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!

MARC

LEADER 00000nab a2200000uu 4500
001 3239024077
003 UK-CbPIL
022 |a 2079-9292 
024 7 |a 10.3390/electronics14152958  |2 doi 
035 |a 3239024077 
045 2 |b d20250101  |b d20251231 
084 |a 231458  |2 nlm 
100 1 |a Long, Ning  |u School of Network and Communication Engineering, Chengdu Technological University, Chengdu 610023, China; longning@cdtu.edu.cn 
245 1 |a BCA-MVSNet: Integrating BIFPN and CA for Enhanced Detail Texture in Multi-View Stereo Reconstruction 
260 |b MDPI AG  |c 2025 
513 |a Journal Article 
520 3 |a The 3D point cloud generated by MVSNet has good scene integrity but lacks sensitivity to details, causing holes and non-dense areas in flat and weak-texture regions. To address this problem and enhance the point cloud information of weak-texture areas, the BCA-MVSNet network is proposed in this paper. The network integrates the Bidirectional Feature Pyramid Network (BIFPN) into the feature processing of the MVSNet backbone network to accurately extract the features of weak-texture regions. In the feature map fusion stage, the Coordinate Attention (CA) mechanism is introduced into 3DU-Net to obtain the position information on the channel dimension related to the direction, improve the detail feature extraction, optimize the depth map and improve the depth accuracy. The experimental results show that BCA-MVSNet not only improves the accuracy of detail texture reconstruction, but also effectively controls the computational overhead. In the DTU dataset, the Overall and Comp metrics of BCA-MVSNet are reduced by 10.2% and 2.6%, respectively; in the Tanksand Temples dataset, the Mean metrics of the eight scenarios are improved by 6.51%. Three scenes are shot by binocular camera, and the reconstruction quality is excellent in the weak-texture area by combining the camera parameters and the BCA-MVSNet model. 
653 |a Feature extraction 
653 |a Accuracy 
653 |a Datasets 
653 |a Cameras 
653 |a Deep learning 
653 |a Image reconstruction 
653 |a Computer vision 
653 |a Computer terminals 
653 |a Neural networks 
653 |a Three dimensional models 
653 |a Feature maps 
653 |a Methods 
653 |a Algorithms 
653 |a Texture 
653 |a Efficiency 
700 1 |a Duan Zhengxu  |u Research Institute of University of Electronic Science and Technology of China, Yibin 644000, China 
700 1 |a Hu, Xiao  |u School of Automation and Information Engineering, Sichuan University of Science and Engineering, Yibin 644005, China; chenmingju@suse.edu.cn 
700 1 |a Chen Mingju  |u School of Automation and Information Engineering, Sichuan University of Science and Engineering, Yibin 644005, China; chenmingju@suse.edu.cn 
773 0 |t Electronics  |g vol. 14, no. 15 (2025), p. 2958-2984 
786 0 |d ProQuest  |t Advanced Technologies & Aerospace Database 
856 4 1 |3 Citation/Abstract  |u https://www.proquest.com/docview/3239024077/abstract/embedded/L8HZQI7Z43R0LA5T?source=fedsrch 
856 4 0 |3 Full Text + Graphics  |u https://www.proquest.com/docview/3239024077/fulltextwithgraphics/embedded/L8HZQI7Z43R0LA5T?source=fedsrch 
856 4 0 |3 Full Text - PDF  |u https://www.proquest.com/docview/3239024077/fulltextPDF/embedded/L8HZQI7Z43R0LA5T?source=fedsrch