{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T15:53:43Z","timestamp":1783612423082,"version":"3.55.0"},"reference-count":42,"publisher":"MDPI AG","issue":"6","license":[{"start":{"date-parts":[[2025,6,9]],"date-time":"2025-06-09T00:00:00Z","timestamp":1749427200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100018555","name":"Science and Technology Plan Project of Guizhou Province","doi-asserted-by":"publisher","award":["Qiankehe Foundation-ZK [2022] General 550"],"award-info":[{"award-number":["Qiankehe Foundation-ZK [2022] General 550"]}],"id":[{"id":"10.13039\/501100018555","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100018555","name":"Science and Technology Plan Project of Guizhou Province","doi-asserted-by":"publisher","award":["JCYJ20220818102215034"],"award-info":[{"award-number":["JCYJ20220818102215034"]}],"id":[{"id":"10.13039\/501100018555","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100018555","name":"Science and Technology Plan Project of Guizhou Province","doi-asserted-by":"publisher","award":["QianJiaoHe KY [2022]298"],"award-info":[{"award-number":["QianJiaoHe KY [2022]298"]}],"id":[{"id":"10.13039\/501100018555","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100018555","name":"Science and Technology Plan Project of Guizhou Province","doi-asserted-by":"publisher","award":["2021YB002"],"award-info":[{"award-number":["2021YB002"]}],"id":[{"id":"10.13039\/501100018555","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shenzhen Science and Technology Program","award":["Qiankehe Foundation-ZK [2022] General 550"],"award-info":[{"award-number":["Qiankehe Foundation-ZK [2022] General 550"]}]},{"name":"Shenzhen Science and Technology Program","award":["JCYJ20220818102215034"],"award-info":[{"award-number":["JCYJ20220818102215034"]}]},{"name":"Shenzhen Science and Technology Program","award":["QianJiaoHe KY [2022]298"],"award-info":[{"award-number":["QianJiaoHe KY [2022]298"]}]},{"name":"Shenzhen Science and Technology Program","award":["2021YB002"],"award-info":[{"award-number":["2021YB002"]}]},{"name":"Youth Science and Technology Talent Growth Project of Guizhou Province","award":["Qiankehe Foundation-ZK [2022] General 550"],"award-info":[{"award-number":["Qiankehe Foundation-ZK [2022] General 550"]}]},{"name":"Youth Science and Technology Talent Growth Project of Guizhou Province","award":["JCYJ20220818102215034"],"award-info":[{"award-number":["JCYJ20220818102215034"]}]},{"name":"Youth Science and Technology Talent Growth Project of Guizhou Province","award":["QianJiaoHe KY [2022]298"],"award-info":[{"award-number":["QianJiaoHe KY [2022]298"]}]},{"name":"Youth Science and Technology Talent Growth Project of Guizhou Province","award":["2021YB002"],"award-info":[{"award-number":["2021YB002"]}]},{"name":"Scientific Research Foundation Project of Guizhou Education University","award":["Qiankehe Foundation-ZK [2022] General 550"],"award-info":[{"award-number":["Qiankehe Foundation-ZK [2022] General 550"]}]},{"name":"Scientific Research Foundation Project of Guizhou Education University","award":["JCYJ20220818102215034"],"award-info":[{"award-number":["JCYJ20220818102215034"]}]},{"name":"Scientific Research Foundation Project of Guizhou Education University","award":["QianJiaoHe KY [2022]298"],"award-info":[{"award-number":["QianJiaoHe KY [2022]298"]}]},{"name":"Scientific Research Foundation Project of Guizhou Education University","award":["2021YB002"],"award-info":[{"award-number":["2021YB002"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Entropy"],"abstract":"<jats:p>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\u2014local 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\u2014LSE-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\u2019s contribution, while cross-domain tests confirm generalization in unseen scenarios. This work establishes a new paradigm for adaptive stereo matching in dynamic environments.<\/jats:p>","DOI":"10.3390\/e27060614","type":"journal-article","created":{"date-parts":[[2025,6,10]],"date-time":"2025-06-10T03:54:18Z","timestamp":1749527658000},"page":"614","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["LSE-CVCNet: A Generalized Stereoscopic Matching Network Based on Local Structural Entropy and Multi-Scale Fusion"],"prefix":"10.3390","volume":"27","author":[{"given":"Wenbang","family":"Yang","sequence":"first","affiliation":[{"name":"State Key Laboratory of Public Big Data, College of Computer Science and Technology, Guizhou University, Guiyang 550025, China"},{"name":"School of Mathematical Sciences, Minzu Normal University of Xingyi, Xingyi 562400, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yong","family":"Zhao","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Public Big Data, College of Computer Science and Technology, Guizhou University, Guiyang 550025, China"},{"name":"Electronic and Computer Engineering School, Shenzhen Graduate School of Peking University, Shenzhen 518055, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ye","family":"Gu","sequence":"additional","affiliation":[{"name":"College of Big Data and Internet, Shenzhen Technology University, Shenzhen 518000, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lu","family":"Huang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Public Big Data, College of Computer Science and Technology, Guizhou University, Guiyang 550025, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianhua","family":"Li","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Public Big Data, College of Computer Science and Technology, Guizhou University, Guiyang 550025, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianchuan","family":"Zhao","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Public Big Data, College of Computer Science and Technology, Guizhou University, Guiyang 550025, China"},{"name":"School of Mathematics and Big Data, Guizhou Education University, Guiyang 550000, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,6,9]]},"reference":[{"key":"ref_1","unstructured":"Dosovitskiy, A., Beyer, L., Fischer, P., and Sumer, S. (2021, January 4). An Image is Worth 16 \u00d7 16 Words: Transformers for Image Recognition at Scale. Proceedings of the International Conference on Learning Representations, Vienna, Austria."},{"key":"ref_2","unstructured":"Poggi, M., Matteucci, M., and Fusiello, A. (2021, January 20\u201325). Attention-Based Stereo Matching with Occlusion Handling. Proceedings of the Conference on Computer Vision and Pattern Recognition, Virtual Conference."},{"key":"ref_3","unstructured":"Zhang, Z., Liu, Y., and Wang, H. (2023, January 23\u201327). Swin Transformer for Stereo Matching. Proceedings of the European Conference on Computer Vision, Tel Aviv, Israel."},{"key":"ref_4","unstructured":"Chen, Z., Xie, X., Liu, W., and Zhang, L. (2022, January 18\u201324). Dynamic Attention Cost Volume Refinement for Stereo Matching. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA."},{"key":"ref_5","unstructured":"Guo, K., Chen, L., and Wang, X. (2023, January 17\u201324). Deformable Cross-Attention for Efficient Stereo Matching. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, BC, Canada."},{"key":"ref_6","first-page":"1234","article-title":"Multi-Head Attention-Based Stereo Matching for Dynamic Scenes","volume":"8","author":"Wang","year":"2023","journal-title":"IEEE Robot. Autom. Lett."},{"key":"ref_7","unstructured":"Liu, J., and Sun, M. (December, January 28). Cross-Domain Attention for Dynamic Stereo Matching. Proceedings of the Thirty-Sixth Annual Conference on Neural Information Processing Systems, New Orleans, LA, USA."},{"key":"ref_8","unstructured":"Zhao, X., Li, Y., and Liu, Z. (2022). Cross-Attention Guided Disparity Estimation. Pattern Recognit. Lett., 161."},{"key":"ref_9","unstructured":"Huang, R., Zhang, L., and Liu, Z. (2021, January 6\u201314). Hybrid Transformer-CNN for Enhanced Stereo Matching. Proceedings of the Thirty-Fifth Conference on Neural Information Processing Systems (NeurIPS 2021), Virtual."},{"key":"ref_10","unstructured":"Sun, C., Xu, H., and Liu, W. (2021, January 11\u201317). Global-Local Attention Fusion for Stereo Matching. Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) 2021, Montreal, QC, Canada."},{"key":"ref_11","unstructured":"Kendall, A., Grimes, M., and Garnett, R. (2020, January 14\u201319). End-to-End Learning of Geometry and Context for Deep Stereo Regression. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2020, Virtual."},{"key":"ref_12","unstructured":"Chang, J., and Chen, Y. (2021, January 19\u201325). PSMNet: Pyramid Stereo Matching Network. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2021, Virtual."},{"key":"ref_13","unstructured":"Zhang, Q., Yang, Z., and Chen, J. (2020, January 6\u201312). Cascade Cost Volume Construction for Stereo Matching. Proceedings of the Conference on Neural Information Processing Systems (NeurIPS) 2020, Virtual."},{"key":"ref_14","first-page":"12345","article-title":"CostVolume Transformer: A Transformer-Based Stereo Matching Framework","volume":"46","author":"Huang","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_15","unstructured":"Tang, T., and Li, S. (2023, January 2\u20136). Adaptive Entropy Weighting for Low-Texture Disparity Estimation. Proceedings of the 2023 International Conference on Computer Vision ICCV 2023, Paris, France."},{"key":"ref_16","unstructured":"Sun, J., and Liu, M. (2023, January 18\u201322). GNN-CostVol: Graph Neural Network-Based Cost Volume Refinement for Occlusion Handling. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2023, Vancouver, BC, Canada."},{"key":"ref_17","unstructured":"Guo, X., Huang, Y., and Li, C. (2022, January 23\u201327). Group-Wise Correlation for Cost Volume Refinement. Proceedings of the European Conference on Computer Vision (ECCV) 2022, Tel Aviv, Israel."},{"key":"ref_18","first-page":"1234","article-title":"Hybrid Optimization for Stereo Matching","volume":"45","author":"Liu","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_19","unstructured":"Xu, L., Liu, S., and Tang, L. (2022, January 27\u201328). Attention-Guided Cost Aggregation for Stereo Matching. Proceedings of the International Conference on Computer Vision (ICCV) 2022, Dubai, United Arab Emirates."},{"key":"ref_20","unstructured":"Zhao, Z., and Wang, Q. (2022, January 23\u201327). Multi-Task Stereo Matching with Semantic Segmentation Integration. Proceedings of the European Conference on Computer Vision (ECCV) 2022, Tel Aviv, Israel."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Chang, T., Yang, X., Zhang, T., and Wang, M. (2023, January 17\u201324). Domain Generalized Stereo Matching via Hierarchical Visual Transformation. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2023, Vancouver, BC, Canada.","DOI":"10.1109\/CVPR52729.2023.00922"},{"key":"ref_22","unstructured":"Chen, C., and Zhang, Y. (2023, January 2\u20136). Cycle-Consistent Contrastive Learning for Self-Supervised Domain Adaptation. Proceedings of the International Conference on Computer Vision (ICCV) 2023, Paris, France."},{"key":"ref_23","unstructured":"Fang, F., and Wang, L. (December, January 28). MAML-Adapt: Few-Shot Meta-Learning for Domain Generalization in Stereo Matching. Proceedings of the The Thirty-Sixth Annual Conference on Neural Information Processing Systems (NeurIPS 2022), New Orleans, LA, USA."},{"key":"ref_24","unstructured":"Lin, H., and Zhang, R. (2024, January 17\u201321). DisparityGAN: Generating Synthetic Disparity Maps for Generalization Enhancement. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2024, Seattle, WA, USA."},{"key":"ref_25","unstructured":"Xu, H., and Zhang, W. (2020). Local Structural Regularization in Stereo Matching. Int. J. Comput. Vis., 128, Early Access."},{"key":"ref_26","unstructured":"Yang, F., Zhang, X., and Li, J. (2021, January 20\u201325). Hierarchical Stereo Matching Network. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2021, Nashville, TN, USA."},{"key":"ref_27","unstructured":"Lin, K., and Zhang, R. (December, January 28). Contrastive Learning for Domain Generalization in Stereo Matching. Proceedings of the Thirty-Sixth Annual Conference on Neural Information Processing Systems (NeurIPS) 2022, New Orleans, LA, USA."},{"key":"ref_28","unstructured":"Wang, H., and Liu, Y. (2023, January 18\u201322). Entropy-Guided Pyramid Fusion for Global-Local Synergy. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2023, Vancouver, BC, Canada."},{"key":"ref_29","unstructured":"Li, J., and Chen, T. (2024, January 20\u201327). Entropy-Regularized Contrastive Learning for Unsupervised Domain Adaptation. Proceedings of the 38th Annual AAAI Conference on Artificial Intelligence (AAAI-2024), Vancouver, BC, Canada."},{"key":"ref_30","unstructured":"Tang, S., Zhang, W., and Chen, J. (2023, January 2\u20136). Local Structural Entropy for Stereo Matching. Proceedings of the International Conference on Computer Vision (ICCV) 2023, Paris, France."},{"key":"ref_31","unstructured":"Li, X., Wang, X., and Zhang, Y. (2021, January 19\u201325). Entropy-Weighted Multi-Scale Fusion for Stereo Disparity Estimation. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2021, Nashville, TN, USA."},{"key":"ref_32","unstructured":"Tzeng, E., Hoffman, J., and Saenko, K. (2020, January 23\u201328). Adversarial Discriminative Domain Adaptation. Proceedings of the European Conference on Computer Vision (ECCV) 2020, Glasgow, UK."},{"key":"ref_33","unstructured":"Zhang, T., Liu, Z., and Wang, H. (2021, January 6\u201314). Domain-Invariant Feature Extraction for Stereo Matching. Proceedings of the Conference on Neural Information Processing Systems (NeurIPS) 2021, Virtual."},{"key":"ref_34","unstructured":"Wang, F., Zhang, Y., and Zhou, Z. (2023, January 24\u201327). Meta-Learning for Cross-Domain Stereo Matching. Proceedings of the International Conference on Learning Representations (ICLR) 2023, Kigali, Rwanda."},{"key":"ref_35","unstructured":"Fang, F., and Wang, L. (December, January 28). MAML-Adapt: Efficient Meta-Learning for Domain Generalization. Proceedings of the Thirty-Sixth Annual Conference on Neural Information Processing Systems (NeurIPS 2022), New Orleans, LA, USA."},{"key":"ref_36","unstructured":"Lin, H., and Zhang, R. (2024, January 17\u201321). DisparityGAN: Generating Synthetic Data for Cross-Domain Generalization. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2024, Seattle, WA, USA."},{"key":"ref_37","unstructured":"Lin, J., Chen, M., and Wang, X. (2024). Generative Adversarial Networks for Cross-Domain Stereo Matching. IEEE Trans. Pattern Anal. Mach. Intell., 45, Early Access."},{"key":"ref_38","unstructured":"Huang, Z., and Yang, H. (2022, January 23\u201327). Domain Generalized Stereo Networks Using Contrastive Learning. Proceedings of the European Conference on Computer Vision (ECCV) 2022, Tel Aviv, Israel."},{"key":"ref_39","unstructured":"Zhao, Q., Li, X., and Zhang, Z. (2022, January 27\u201328). Unsupervised Domain Adaptation for Stereo Matching. Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) 2022, Dubai, United Arab Emirates."},{"key":"ref_40","first-page":"123","article-title":"Local Context Enhancement for Stereo Matching via Dilated Convolutions","volume":"47","author":"Chang","year":"2018","journal-title":"Int. J. Robot. Res."},{"key":"ref_41","first-page":"479","article-title":"A fast learning algorithm for deep belief nets","volume":"19","author":"Hinton","year":"2006","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_42","unstructured":"Bishop, C.M. (2006). Global entropy minimization. Pattern Recognition and Machine Learning, Springer."}],"container-title":["Entropy"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1099-4300\/27\/6\/614\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T17:49:02Z","timestamp":1760032142000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1099-4300\/27\/6\/614"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,9]]},"references-count":42,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2025,6]]}},"alternative-id":["e27060614"],"URL":"https:\/\/doi.org\/10.3390\/e27060614","relation":{},"ISSN":["1099-4300"],"issn-type":[{"value":"1099-4300","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,9]]}}}