Next Article in Journal
Efficient Entanglement Swapping in Quantum Networks for Multi-User Scenarios
Previous Article in Journal
Long-Range Dependence in Word Time Series: The Cosine Correlation of Embeddings
 
 
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Article

LSE-CVCNet: A Generalized Stereoscopic Matching Network Based on Local Structural Entropy and Multi-Scale Fusion

1
State Key Laboratory of Public Big Data, College of Computer Science and Technology, Guizhou University, Guiyang 550025, China
2
School of Mathematical Sciences, Minzu Normal University of Xingyi, Xingyi 562400, China
3
Electronic and Computer Engineering School, Shenzhen Graduate School of Peking University, Shenzhen 518055, China
4
College of Big Data and Internet, Shenzhen Technology University, Shenzhen 518000, China
5
School of Mathematics and Big Data, Guizhou Education University, Guiyang 550000, China
*
Authors to whom correspondence should be addressed.
Entropy 2025, 27(6), 614; https://doi.org/10.3390/e27060614 (registering DOI)
Submission received: 8 April 2025 / Revised: 28 May 2025 / Accepted: 29 May 2025 / Published: 9 June 2025
(This article belongs to the Section Multidisciplinary Applications)

Abstract

This study presents LSE-CVCNet, a novel stereo matching network designed to resolve challenges in dynamic scenes, including dynamic feature misalignment caused by texture variability and contextual ambiguity from occlusions. By integrating three key innovations—local structural entropy (LSE) to quantify structural uncertainty in disparity maps and guide adaptive attention, a cross-image attention mechanism (CIAM-T) to asymmetrically extract features from left/right images for improved feature alignment, and multi-resolution cost volume fusion (MRCV-F) to preserve fine-grained details through multi-scale fusion—LSE-CVCNet enhances disparity estimation accuracy and cross-domain generalization. The experimental results demonstrate robustness under varying lighting, occlusions, and complex geometries, outperforming state-of-the-art methods across multiple data sets. Ablation studies validate each module’s contribution, while cross-domain tests confirm generalization in unseen scenarios. This work establishes a new paradigm for adaptive stereo matching in dynamic environments.
Keywords: stereo matching; local structural entropy; cross-image attention; multi-resolution fusion; dynamic scenes; contextual ambiguity; cross-domain generalization stereo matching; local structural entropy; cross-image attention; multi-resolution fusion; dynamic scenes; contextual ambiguity; cross-domain generalization

Share and Cite

MDPI and ACS Style

Yang, W.; Zhao, Y.; Gu, Y.; Huang, L.; Li, J.; Zhao, J. LSE-CVCNet: A Generalized Stereoscopic Matching Network Based on Local Structural Entropy and Multi-Scale Fusion. Entropy 2025, 27, 614. https://doi.org/10.3390/e27060614

AMA Style

Yang W, Zhao Y, Gu Y, Huang L, Li J, Zhao J. LSE-CVCNet: A Generalized Stereoscopic Matching Network Based on Local Structural Entropy and Multi-Scale Fusion. Entropy. 2025; 27(6):614. https://doi.org/10.3390/e27060614

Chicago/Turabian Style

Yang, Wenbang, Yong Zhao, Ye Gu, Lu Huang, Jianhua Li, and Jianchuan Zhao. 2025. "LSE-CVCNet: A Generalized Stereoscopic Matching Network Based on Local Structural Entropy and Multi-Scale Fusion" Entropy 27, no. 6: 614. https://doi.org/10.3390/e27060614

APA Style

Yang, W., Zhao, Y., Gu, Y., Huang, L., Li, J., & Zhao, J. (2025). LSE-CVCNet: A Generalized Stereoscopic Matching Network Based on Local Structural Entropy and Multi-Scale Fusion. Entropy, 27(6), 614. https://doi.org/10.3390/e27060614

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Article metric data becomes available approximately 24 hours after publication online.
Back to TopTop