Have a personal or library account? Click to login
Research on Multi-View Stereo Network Based on Self-Attention Mechanism Cover

Research on Multi-View Stereo Network Based on Self-Attention Mechanism

By: Wenkai Li,  Jun Yu,  Leilei Fan and  Zhiyi Hu  
Open Access
|Sep 2025

Abstract

As the technologies of virtual reality and augmented reality rapidly advance, the demand for high-quality 3D models has been growing exponentially. However, the Multi-View Stereo Network (MVSNet) for 3D reconstruction has faced issues with the inaccurate extraction of global image information and depth cues. In response to these challenges, this paper presents enhancements to MVSNet. First, the self-attention mechanism is introduced to enhance MVSNet's ability to capture global information in images. Second, a residual structure is added to mitigate the accuracy loss caused by the downsampling and upsampling of feature maps during the regularization process of cost volume, thus ensuring the integrity of information and transmission efficiency. Experimental results indicate that, in comparison with the original MVSNet, the SelfRes-MVSNet reduces the error rate by 1.3% in terms of overall accuracy and completeness, thereby improving the reconstruction effect from 2D images to 3D models.

Language: English
Page range: 1 - 10
Published on: Sep 30, 2025
Published by: Xi’an Technological University
In partnership with: Paradigm Publishing Services
Publication frequency: 4 issues per year

© 2025 Wenkai Li, Jun Yu, Leilei Fan, Zhiyi Hu, published by Xi’an Technological University
This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License.