Wenqu Zhao, Lingxue Wang, Lian Zhang, Dezhi Zheng, Yi Cai
{"title":"CGMRF: CLIP-guide多模态配准与融合的可见-红外双模成像系统。","authors":"Wenqu Zhao, Lingxue Wang, Lian Zhang, Dezhi Zheng, Yi Cai","doi":"10.1364/OL.558572","DOIUrl":null,"url":null,"abstract":"<p><p>In this Letter, we propose CLIP-guided multimodal registration and fusion (CGMRF), a semantic understanding-based multimodal image fusion system, for visible and infrared (IR) dual-modality imaging. CGMRF leverages semantic similarity, better aligned with human visual interpretation, to address the challenges of multimodal image registration and fusion. Experimental results across multiple metrics demonstrate the advantages of the proposed CGMRF system.</p>","PeriodicalId":19540,"journal":{"name":"Optics letters","volume":"50 12","pages":"3907-3910"},"PeriodicalIF":3.3000,"publicationDate":"2025-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"CGMRF: CLIP-guide multimodal registration and fusion for a visible-infrared dual-modality imaging system.\",\"authors\":\"Wenqu Zhao, Lingxue Wang, Lian Zhang, Dezhi Zheng, Yi Cai\",\"doi\":\"10.1364/OL.558572\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>In this Letter, we propose CLIP-guided multimodal registration and fusion (CGMRF), a semantic understanding-based multimodal image fusion system, for visible and infrared (IR) dual-modality imaging. CGMRF leverages semantic similarity, better aligned with human visual interpretation, to address the challenges of multimodal image registration and fusion. Experimental results across multiple metrics demonstrate the advantages of the proposed CGMRF system.</p>\",\"PeriodicalId\":19540,\"journal\":{\"name\":\"Optics letters\",\"volume\":\"50 12\",\"pages\":\"3907-3910\"},\"PeriodicalIF\":3.3000,\"publicationDate\":\"2025-06-15\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Optics letters\",\"FirstCategoryId\":\"101\",\"ListUrlMain\":\"https://doi.org/10.1364/OL.558572\",\"RegionNum\":2,\"RegionCategory\":\"物理与天体物理\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"OPTICS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Optics letters","FirstCategoryId":"101","ListUrlMain":"https://doi.org/10.1364/OL.558572","RegionNum":2,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"OPTICS","Score":null,"Total":0}
CGMRF: CLIP-guide multimodal registration and fusion for a visible-infrared dual-modality imaging system.
In this Letter, we propose CLIP-guided multimodal registration and fusion (CGMRF), a semantic understanding-based multimodal image fusion system, for visible and infrared (IR) dual-modality imaging. CGMRF leverages semantic similarity, better aligned with human visual interpretation, to address the challenges of multimodal image registration and fusion. Experimental results across multiple metrics demonstrate the advantages of the proposed CGMRF system.
期刊介绍:
The Optical Society (OSA) publishes high-quality, peer-reviewed articles in its portfolio of journals, which serve the full breadth of the optics and photonics community.
Optics Letters offers rapid dissemination of new results in all areas of optics with short, original, peer-reviewed communications. Optics Letters covers the latest research in optical science, including optical measurements, optical components and devices, atmospheric optics, biomedical optics, Fourier optics, integrated optics, optical processing, optoelectronics, lasers, nonlinear optics, optical storage and holography, optical coherence, polarization, quantum electronics, ultrafast optical phenomena, photonic crystals, and fiber optics. Criteria used in determining acceptability of contributions include newsworthiness to a substantial part of the optics community and the effect of rapid publication on the research of others. This journal, published twice each month, is where readers look for the latest discoveries in optics.