{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T04:07:27Z","timestamp":1778818047180,"version":"3.51.4"},"reference-count":54,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100004829","name":"Science and Technology Department of Sichuan Province","doi-asserted-by":"publisher","award":["2021YFG0380"],"award-info":[{"award-number":["2021YFG0380"]}],"id":[{"id":"10.13039\/501100004829","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Applied Soft Computing"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1016\/j.asoc.2026.115074","type":"journal-article","created":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T08:41:20Z","timestamp":1773909680000},"page":"115074","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Mamba-enhanced multi-view stereo: Geometry-aware feature fusion and 3D cost volume regularization"],"prefix":"10.1016","volume":"195","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4785-3145","authenticated-orcid":false,"given":"Liangliang","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-7631-9736","authenticated-orcid":false,"given":"Guihua","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Feng","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenjin","family":"Liao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenjie","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"issue":"1-2","key":"10.1016\/j.asoc.2026.115074_bib1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1561\/0600000052","article-title":"Multi-view stereo: a tutorial","volume":"9","author":"Furukawa","year":"2015","journal-title":"Found. Trends\u00ae Comput. Graph. Vis."},{"issue":"2","key":"10.1016\/j.asoc.2026.115074_bib2","doi-asserted-by":"crossref","first-page":"85","DOI":"10.62762\/TSCC.2024.554721","article-title":"3D holography advertisement on vehicle using IoT","volume":"2","author":"Farooq","year":"2025","journal-title":"ICCK Trans. Sens. Commun. Control"},{"issue":"1","key":"10.1016\/j.asoc.2026.115074_bib3","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1007\/BF01428192","article-title":"Object-centered surface reconstruction: combining multi-image stereo and shading","volume":"16","author":"Fua","year":"1995","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.asoc.2026.115074_bib4","series-title":"Proceedings of the IEEE International Conference on Computer Vision","first-page":"873","article-title":"Massively parallel multiview stereopsis by surface normal diffusion","author":"Galliani","year":"2015"},{"key":"10.1016\/j.asoc.2026.115074_bib5","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"4104","article-title":"Structure-from-motion revisited","author":"Schonberger","year":"2016"},{"key":"10.1016\/j.asoc.2026.115074_bib6","series-title":"Computer Vision\u2013ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part III 14","first-page":"501","article-title":"Pixelwise view selection for unstructured multi-view stereo","author":"Sch\u00f6nberger","year":"2016"},{"key":"10.1016\/j.asoc.2026.115074_bib7","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2024.127553","article-title":"Multi-view 3D reconstruction based on deep learning: a survey and comparison of methods","volume":"582","author":"Wu","year":"2024","journal-title":"Neurocomputing"},{"key":"10.1016\/j.asoc.2026.115074_bib8","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"2524","article-title":"Deep stereo using adaptive thin volume representation with uncertainty awareness","author":"Cheng","year":"2020"},{"key":"10.1016\/j.asoc.2026.115074_bib9","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"4877","article-title":"Cost volume pyramid based depth inference for multi-view stereo","author":"Yang","year":"2020"},{"key":"10.1016\/j.asoc.2026.115074_bib10","series-title":"Proceedings of the european conference on computer vision (ECCV)","first-page":"767","article-title":"Mvsnet: depth inference for unstructured multi-view stereo","author":"Yao","year":"2018"},{"key":"10.1016\/j.asoc.2026.115074_bib11","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"5525","article-title":"Recurrent mvsnet for high-resolution multi-view stereo depth inference","author":"Yao","year":"2019"},{"key":"10.1016\/j.asoc.2026.115074_bib12","doi-asserted-by":"crossref","first-page":"153","DOI":"10.1007\/s11263-016-0902-9","article-title":"Large-scale data for multiple-view stereopsis","volume":"120","author":"Aan\u00e6s","year":"2016","journal-title":"Int. J. Comput. Vis."},{"issue":"4","key":"10.1016\/j.asoc.2026.115074_bib13","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3072959.3073599","article-title":"Tansks & temples: benchmarking large-scale scene reconstruction","volume":"36","author":"Knapitsch","year":"2017","journal-title":"ACM Trans. Graph. (ToG)"},{"key":"10.1016\/j.asoc.2026.115074_bib14","first-page":"29","article-title":"Understanding the effective receptive field in deep convolutional neural networks","author":"Luo","year":"2016","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.asoc.2026.115074_bib15","series-title":"Proceedings of the IEEE International Conference on Computer Vision","first-page":"764","article-title":"Deformable convolutional networks","author":"Dai","year":"2017"},{"key":"10.1016\/j.asoc.2026.115074_bib16","unstructured":"Bahdanau D. Neural machine translation by jointly learning to align and translate. arxiv preprint arxiv:1409.0473, 2014."},{"key":"10.1016\/j.asoc.2026.115074_bib17","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.asoc.2026.115074_bib18","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"8585","article-title":"Transmvsnet: global context-aware multi-view stereo network with transformers","author":"Ding","year":"2022"},{"key":"10.1016\/j.asoc.2026.115074_bib19","article-title":"Transformer-guided feature pyramid network for multi-view stereo","author":"Wang","year":"2024","journal-title":"Neurocomputing"},{"key":"10.1016\/j.asoc.2026.115074_bib20","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"18088","article-title":"When epipolar constraint meets non-local operators in multi-view stereo","author":"Liu","year":"2023"},{"key":"10.1016\/j.asoc.2026.115074_bib21","unstructured":"Gu A., Dao T. Mamba: Linear-time sequence modeling with selective state spaces. arxiv preprint arxiv:2312.00752, 2023."},{"key":"10.1016\/j.asoc.2026.115074_bib22","doi-asserted-by":"crossref","unstructured":"Zhang Y., Li R., Liang X., et al. MamNet: A Novel Hybrid Model for Time-Series Forecasting and Frequency Pattern Analysis in Network Traffic. ICCK Transactions on Intelligent Systematics, 2(2), 109\u2013124.","DOI":"10.62762\/TIS.2025.347925"},{"key":"10.1016\/j.asoc.2026.115074_bib23","unstructured":"Zhu L., Liao B., Zhang Q., et al. Vision mamba: Efficient visual representation learning with bidirectional state space model. arxiv preprint arxiv:2401.09417, 2024."},{"key":"10.1016\/j.asoc.2026.115074_bib24","unstructured":"Y. Liu, Y. Tian, Y. Zhao, et al. Vmamba: Visual state space model. arxiv preprint arxiv:2401.10166, 2024."},{"issue":"11","key":"10.1016\/j.asoc.2026.115074_bib25","doi-asserted-by":"crossref","first-page":"7632","DOI":"10.1109\/TCSVT.2022.3180274","article-title":"MoADNet: mobile asymmetric dual-stream networks for real-time and lightweight RGB-D salient object detection","volume":"32","author":"Jin","year":"2022","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.asoc.2026.115074_bib26","doi-asserted-by":"crossref","first-page":"414","DOI":"10.1016\/j.neucom.2022.04.015","article-title":"FCMNet: frequency-aware cross-modality attention networks for RGB-D salient object detection","volume":"491","author":"Jin","year":"2022","journal-title":"Neurocomputing"},{"issue":"1","key":"10.1016\/j.asoc.2026.115074_bib27","doi-asserted-by":"crossref","first-page":"3","DOI":"10.62762\/TSCC.2024.989358","article-title":"Innovations in 3D object detection: a comprehensive review of methods, sensor fusion, and future directions","volume":"1","author":"Abro","year":"2024","journal-title":"ICCK Trans. Sens. Commun. Control"},{"key":"10.1016\/j.asoc.2026.115074_bib28","doi-asserted-by":"crossref","unstructured":"Liu B., Li R., Zhou L., et al. Dt-nerf: a diffusion and transformer-based optimization approach for neural radiance fields in 3d reconstruction. ICCK Transactions on Intelligent Systematics, 2(3), 190\u2013202.","DOI":"10.62762\/TIS.2025.874668"},{"issue":"4","key":"10.1016\/j.asoc.2026.115074_bib29","doi-asserted-by":"crossref","first-page":"1678","DOI":"10.1109\/TCDS.2021.3135948","article-title":"Visual sentiment classification via low-rank regularization and label relaxation","volume":"14","author":"Jin","year":"2021","journal-title":"IEEE Trans. Cogn. Dev. Syst."},{"key":"10.1016\/j.asoc.2026.115074_bib30","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2024.129129","article-title":"DFD-NAS: general deepfake detection via efficient neural architecture search","volume":"619","author":"Jin","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.asoc.2026.115074_bib31","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2024.128607","article-title":"Image manipulation localization via dynamic cross-modality fusion and progressive integration","volume":"610","author":"Jin","year":"2024","journal-title":"Neurocomputing"},{"key":"10.1016\/j.asoc.2026.115074_bib32","series-title":"European Conference on Computer Vision","first-page":"75","article-title":"Mamba-nd: selective state space modeling for multi-dimensional data","author":"Li","year":"2025"},{"key":"10.1016\/j.asoc.2026.115074_bib33","series-title":"European Conference on Computer Vision","first-page":"222","article-title":"Mambair: a simple baseline for image restoration with state-space model","author":"Guo","year":"2025"},{"key":"10.1016\/j.asoc.2026.115074_bib34","series-title":"European Conference on Computer Vision","first-page":"237","article-title":"Videomamba: state space model for efficient video understanding","author":"Li","year":"2025"},{"key":"10.1016\/j.asoc.2026.115074_bib35","series-title":"European Conference on Computer Vision","first-page":"148","article-title":"Zigma: a dit-style zigzag mamba diffusion model","author":"Hu","year":"2025"},{"key":"10.1016\/j.asoc.2026.115074_bib36","series-title":"Proceedings of the IEEE International Conference on Computer Vision","first-page":"2307","article-title":"Surfacenet: an end-to-end 3D neural network for multiview stereopsis","author":"Ji","year":"2017"},{"key":"10.1016\/j.asoc.2026.115074_bib37","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"2495","article-title":"Cascade cost volume for high-resolution multi-view stereo and stereo matching","author":"Gu","year":"2020"},{"key":"10.1016\/j.asoc.2026.115074_bib38","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"8626","article-title":"Non-parametric depth distribution modelling based depth inference for multi-view stereo","author":"Yang","year":"2022"},{"key":"10.1016\/j.asoc.2026.115074_bib39","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"20207","article-title":"Gomvs: geometrically consistent cost aggregation for multi-view stereo","author":"Wu","year":"2024"},{"key":"10.1016\/j.asoc.2026.115074_bib40","unstructured":"Cao C., Ren X., Fu Y. MVSFormer++: Revealing the Devil in Transformer's Details for Multi-View Stereo. arXiv preprint arXiv:2401.11673, 2024."},{"key":"10.1016\/j.asoc.2026.115074_bib41","unstructured":"Oquab M., Darcet T., Moutakanni T., et al. Dinov2: Learning robust visual features without supervision. arXiv preprint arXiv:2304.07193, 2023."},{"key":"10.1016\/j.asoc.2026.115074_bib42","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"2980","article-title":"Focal loss for dense object detection","author":"Ross","year":"2017"},{"key":"10.1016\/j.asoc.2026.115074_bib43","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"5732","article-title":"Epp-mvsnet: epipolar-assembling based depth prediction for multi-view stereo","author":"Ma","year":"2021"},{"key":"10.1016\/j.asoc.2026.115074_bib44","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"1790","article-title":"Blendedmvs: a large-scale dataset for generalized multi-view stereo networks","author":"Yao","year":"2020"},{"key":"10.1016\/j.asoc.2026.115074_bib45","series-title":"European Conference on Computer Vision","first-page":"674","article-title":"Dense hybrid recurrent multi-view stereo net with dynamic consistency checking","author":"Yan","year":"2020"},{"key":"10.1016\/j.asoc.2026.115074_bib46","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"8595","article-title":"Raymvsnet: learning ray-based 1D implicit fields for accurate multi-view stereo","author":"Xi","year":"2022"},{"key":"10.1016\/j.asoc.2026.115074_bib47","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"8655","article-title":"Efficient multi-view stereo by iterative dynamic cost volume","author":"Wang","year":"2022"},{"key":"10.1016\/j.asoc.2026.115074_bib48","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"8645","article-title":"Rethinking depth estimation for multi-view stereo: A unified representation","author":"Peng","year":"2022"},{"key":"10.1016\/j.asoc.2026.115074_bib49","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"12991","article-title":"Generalized binary search network for highly-efficient multi-view stereo","author":"Mi","year":"2022"},{"key":"10.1016\/j.asoc.2026.115074_bib50","series-title":"European Conference on Computer Vision","first-page":"573","article-title":"Mvster: Epipolar transformer for efficient multi-view stereo","author":"Wang","year":"2022"},{"key":"10.1016\/j.asoc.2026.115074_bib51","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2023.109885","article-title":"ARAI-MVSNet: a multi-view stereo depth estimation network with adaptive depth range and depth interval","volume":"144","author":"Zhang","year":"2023","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.asoc.2026.115074_bib52","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"21508","article-title":"Geomvsnet: Learning multi-view stereo with geometry perception","author":"Zhang","year":"2023"},{"key":"10.1016\/j.asoc.2026.115074_bib53","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1016\/j.patrec.2024.07.008","article-title":"HC-MVSNet: a probability sampling-based multi-view-stereo network with hybrid cascade structure for 3D reconstruction","volume":"185","author":"Gao","year":"2024","journal-title":"Pattern Recognit. Lett."},{"issue":"10","key":"10.1016\/j.asoc.2026.115074_bib54","doi-asserted-by":"crossref","first-page":"9414","DOI":"10.1109\/TCSVT.2024.3398060","article-title":"Efficient multi-view stereo by dynamic cost volume and cross-scale propagation","volume":"34","author":"Wang","year":"2024","journal-title":"IEEE Trans. Circuits Syst. Video Technol."}],"container-title":["Applied Soft Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1568494626005223?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1568494626005223?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T03:12:18Z","timestamp":1778814738000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1568494626005223"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":54,"alternative-id":["S1568494626005223"],"URL":"https:\/\/doi.org\/10.1016\/j.asoc.2026.115074","relation":{},"ISSN":["1568-4946"],"issn-type":[{"value":"1568-4946","type":"print"}],"subject":[],"published":{"date-parts":[[2026,6]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Mamba-enhanced multi-view stereo: Geometry-aware feature fusion and 3D cost volume regularization","name":"articletitle","label":"Article Title"},{"value":"Applied Soft Computing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.asoc.2026.115074","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"115074"}}