{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T15:19:16Z","timestamp":1785424756344,"version":"3.56.0"},"reference-count":20,"publisher":"Optica Publishing Group","issue":"2","license":[{"start":{"date-parts":[[2026,1,23]],"date-time":"2026-01-23T00:00:00Z","timestamp":1769126400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/doi.org\/10.1364\/OA_License_v2#VOR-OA"},{"start":{"date-parts":[[2026,1,23]],"date-time":"2026-01-23T00:00:00Z","timestamp":1769126400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/opg.optica.org\/policies\/opg-tdm-policy.json"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62021005"],"award-info":[{"award-number":["62021005"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"},{"id":"https:\/\/ror.org\/01h0zpd94","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":["opg.optica.org"],"crossmark-restriction":false},"short-container-title":["Opt. Express"],"published-print":{"date-parts":[[2026,1,26]]},"abstract":"<jats:p>Multimodal 3D semantic segmentation plays a crucial role in engineering applications such as autonomous driving, robotics, and 3D image acquisition and display systems. However, the complex geometry of real scenes, varying object scales, and the inherent sparsity and non-uniform sampling of LiDAR-based acquisition still present significant challenges. To address these issues, we propose an adaptive geometry fusion method for robust and efficient multimodal 3D understanding. The method adopts a dual-path 3D feature extractor: one path captures spatial structural relationships through position-based encoding, while the other integrates a geometry-aware adaptive aggregation module that models local structures using learnable kernel positions and hybrid distance\u2013appearance weighting. Complementary image features from passive optical imaging are fused with LiDAR features to enhance semantic discrimination in regions with sparse or ambiguous 3D measurements. The overall framework remains lightweight, containing only 5.2M parameters, and achieves real-time inference at 25\u2005ms per sample, enabling deployment in resource-constrained sensing and visualization platforms. Experiments on Semantic3D, SemanticKITTI (71.2% mIoU, surpassing the lightweight baseline RandLA-Net by 15.3%), and nuScenes demonstrate competitive performance and strong generalization. Furthermore, evaluations on real-world colored point clouds acquired from a LiDAR\u2013camera system validate the effectiveness of the proposed method in outdoor environments, providing semantically structured 3D representations suitable for downstream 3D display and visualization applications.<\/jats:p>","DOI":"10.1364\/oe.585727","type":"journal-article","created":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T05:00:06Z","timestamp":1767330006000},"page":"3444","update-policy":"https:\/\/doi.org\/10.1364\/crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Geometry-aware multimodal fusion for large-scale 3D scene understanding"],"prefix":"10.1364","volume":"34","author":[{"given":"Yuhao","family":"Wang","sequence":"first","affiliation":[{"id":[{"id":"https:\/\/ror.org\/04w9fbh59","id-type":"ROR","asserted-by":"publisher"}]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yong","family":"Zuo","sequence":"additional","affiliation":[{"id":[{"id":"https:\/\/ror.org\/04w9fbh59","id-type":"ROR","asserted-by":"publisher"}]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi","family":"Tang","sequence":"additional","affiliation":[{"name":"Beijing Institute of Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7178-686X","authenticated-orcid":true,"given":"Xiaobin","family":"Hong","sequence":"additional","affiliation":[{"id":[{"id":"https:\/\/ror.org\/04w9fbh59","id-type":"ROR","asserted-by":"publisher"}]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jian","family":"Wu","sequence":"additional","affiliation":[{"id":[{"id":"https:\/\/ror.org\/04w9fbh59","id-type":"ROR","asserted-by":"publisher"}]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziyu","family":"Bian","sequence":"additional","affiliation":[{"name":"Beijing Institute of Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"285","published-online":{"date-parts":[[2026,1,23]]},"reference":[{"key":"oe-34-2-3444-R1","doi-asserted-by":"publisher","first-page":"105474","DOI":"10.1016\/j.engappai.2022.105474","type":"journal-article","volume":"116","author":"Hu","year":"2022","journal-title":"Engineering Applications of Artificial Intelligence"},{"key":"oe-34-2-3444-R2","doi-asserted-by":"publisher","first-page":"105169","DOI":"10.1016\/j.cities.2024.105169","type":"journal-article","volume":"152","author":"Ito","year":"2024","journal-title":"Cities"},{"key":"oe-34-2-3444-R4","doi-asserted-by":"publisher","first-page":"66","DOI":"10.1007\/s11263-015-0824-y","type":"journal-article","volume":"116","author":"Guo","year":"2016","journal-title":"Int. J. Comput. Vis."},{"key":"oe-34-2-3444-R5","doi-asserted-by":"publisher","first-page":"354","DOI":"10.1016\/j.patcog.2017.10.013","type":"journal-article","volume":"77","author":"Gu","year":"2018","journal-title":"Pattern Recognition"},{"key":"oe-34-2-3444-R7","doi-asserted-by":"publisher","first-page":"108550","DOI":"10.1016\/j.engappai.2024.108550","type":"journal-article","volume":"133","author":"Thakur","year":"2024","journal-title":"Engineering Applications of Artificial Intelligence"},{"key":"oe-34-2-3444-R8","doi-asserted-by":"publisher","first-page":"102926","DOI":"10.1016\/j.jag.2022.102926","type":"journal-article","volume":"112","author":"Li","year":"2022","journal-title":"International Journal of Applied Earth Observation and Geoinformation"},{"key":"oe-34-2-3444-R9","doi-asserted-by":"publisher","first-page":"102317","DOI":"10.1016\/j.inffus.2024.102317","type":"journal-article","volume":"107","author":"Fadhel","year":"2024","journal-title":"Information Fusion"},{"key":"oe-34-2-3444-R17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3674501","type":"journal-article","volume":"56","author":"Zhao","year":"2024","journal-title":"ACM Comput. Surv."},{"key":"oe-34-2-3444-R21","doi-asserted-by":"publisher","first-page":"6327","DOI":"10.3390\/s23146327","type":"journal-article","volume":"23","author":"Wang","year":"2023","journal-title":"Sensors"},{"key":"oe-34-2-3444-R23","doi-asserted-by":"publisher","first-page":"103391","DOI":"10.1016\/j.jag.2023.103391","type":"journal-article","volume":"122","author":"Li","year":"2023","journal-title":"International Journal of Applied Earth Observation and Geoinformation"},{"key":"oe-34-2-3444-R24","doi-asserted-by":"publisher","first-page":"108361","DOI":"10.1016\/j.engappai.2024.108361","type":"journal-article","volume":"133","author":"Wang","year":"2024","journal-title":"Engineering Applications of Artificial Intelligence"},{"key":"oe-34-2-3444-R26","doi-asserted-by":"publisher","first-page":"4036035","DOI":"10.1155\/2022\/4036035","type":"journal-article","volume":"2022","author":"Bansal","year":"2022","journal-title":"Contrast Media Mol. Imaging"},{"key":"oe-34-2-3444-R27","doi-asserted-by":"publisher","author":"Huang","year":"2021","DOI":"10.48550\/arXiv.2103.02690","type":"preprint"},{"key":"oe-34-2-3444-R28","first-page":"104730","volume":"132","author":"Yu","year":"2023"},{"key":"oe-34-2-3444-R29","doi-asserted-by":"publisher","first-page":"121778","DOI":"10.1016\/j.eswa.2023.121778","type":"journal-article","volume":"238","author":"Liang","year":"2024","journal-title":"Expert Systems with Applications"},{"key":"oe-34-2-3444-R30","doi-asserted-by":"publisher","first-page":"111384","DOI":"10.1016\/j.engappai.2025.111384","type":"journal-article","volume":"157","author":"Zhu","year":"2025","journal-title":"Engineering Applications of Artificial Intelligence"},{"key":"oe-34-2-3444-R31","doi-asserted-by":"publisher","author":"Hackel","year":"2017","DOI":"10.48550\/arXiv.1704.03847","type":"preprint"},{"key":"oe-34-2-3444-R35","doi-asserted-by":"publisher","first-page":"2069","DOI":"10.1109\/TMM.2023.3291823","type":"journal-article","volume":"26","author":"Wan","year":"2024","journal-title":"IEEE Trans. Multimedia"},{"key":"oe-34-2-3444-R38","doi-asserted-by":"publisher","author":"Zhou","year":"2020","DOI":"10.48550\/arXiv.2008.01550","type":"preprint"},{"key":"oe-34-2-3444-R42","first-page":"3","author":"Woo","year":"2018"}],"container-title":["Optics Express"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/opg.optica.org\/viewmedia.cfm?URI=oe-34-2-3444&seq=0","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T13:03:34Z","timestamp":1778677414000},"score":1,"resource":{"primary":{"URL":"https:\/\/opg.optica.org\/abstract.cfm?URI=oe-34-2-3444"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,23]]},"references-count":20,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2026]]},"published-print":{"date-parts":[[2026]]}},"URL":"https:\/\/doi.org\/10.1364\/oe.585727","relation":{},"ISSN":["1094-4087"],"issn-type":[{"value":"1094-4087","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,23]]},"assertion":[{"value":"Optica Publishing Group","name":"publisher","label":"This article is maintained by"},{"value":"https:\/\/doi.org\/10.1364\/OE.585727","name":"articlelink","label":"Crossref DOI link to publisher maintained version"},{"value":"research-article","name":"content_type","label":"Article type"},{"value":"Screened by Similarity Check","name":"cross_check","label":"Similarity check"},{"value":"Yes","order":0,"name":"peer_reviewed","label":"Peer reviewed","group":{"name":"peer_review","label":"Peer review"}},{"value":"Single blind","order":1,"name":"review_process","label":"Review process","group":{"name":"peer_review","label":"Peer review"}},{"value":"25 November 2025","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"29 December 2025","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"23 January 2026","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}},{"value":"\u00a9 2026 Optica Publishing Group under the terms of the Optica Open Access Publishing Agreement","name":"copyright","label":"Copyright"}]}}