arXivDaily arXiv每日学术速递 周一至周五更新

视觉与机器人

多模态信息融合

面向图像、视频、多传感器和跨模态感知的信息融合,包括 Image Fusion、红外可见光、遥感、医学影像、LiDAR/雷达/相机和音视频融合。

共收录 533 信号源:cs.CV, eess.IV, eess.SP, cs.RO, cs.MM

1. 红外-可见光融合 533 篇

2606.01836 2026-06-02 eess.IV 79%

Face Liveness Detection Using RGB and Thermal Image Fusion

使用RGB和热成像融合的人脸活体检测

Merve Erşan, Melike Girgin, Tayfun Akgül

专题命中 红外-可见光融合 :image fusion(title);multimodal fusion(abstract);分类 eess.IV

AI总结 提出一种融合RGB图像边缘信息与热成像的方法,利用自定义ARISTOF数据集和YOLOv8-Face模型,有效提升人脸活体检测的鲁棒性。

Comments Published in ELECO 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2208.00967 2026-06-02 cs.CV 79%

Counterfactual Intervention Feature Transfer for Visible-Infrared Person Re-identification

反事实干预特征迁移用于可见光-红外行人重识别

Xulin Li, Yan Lu, Bin Liu, Yating Liu, Guojun Yin, Qi Chu, Jinyang Huang, Feng Zhu, Rui Zhao, Nenghai Yu

机构 * School of Information Science and Technology, University of Science and Technology of China(信息科学与技术学院,中国科学技术大学) Key Laboratory of Electromagnetic Space Information, Chinese Academy of Science(电磁空间信息重点实验室,中国科学院) School of Data Science, University of Science and Technology of China(数据科学学院,中国科学技术大学) SenseTime Research(商汤科技研究院) Qing Yuan Research Institute, Shanghai Jiao Tong University(青元研究院,上海交通大学)

专题命中 红外-可见光融合 :visible-infrared(title,abstract);分类 cs.CV

AI总结 针对可见光-红外行人重识别中图模型泛化性差的问题,提出反事实干预特征迁移方法,通过同质与异质特征迁移减少模态不平衡,并利用反事实关系干预增强图拓扑结构的可靠性。

Comments Accepted by ECCV 2022

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.22273 2026-05-22 cs.CV 79%

Exposing Vulnerabilities in Visible-Infrared VLMs: A Unified Geometric Adversarial Framework with Cross-Task Transferability

揭示可见-红外VLMs中的漏洞:一种具有跨任务迁移性的统一几何对抗框架

Xiang Chen, Yuxian Dong, Chao Li, Chengyin Hu, Jiaju Han, Fengyu Zhang, Yiwei Wei, Jiahuan Long, Jiujiang Guo

专题命中 红外-可见光融合 :visible-infrared(title,abstract);分类 cs.CV

AI总结 本文针对可见-红外视觉语言模型在多模态任务中的对抗鲁棒性不足问题,提出了一种基于分形几何的对抗框架CFGPatch,通过引入曲边分形元素和Fraser螺旋渲染机制,有效攻击VLMs并展示出跨任务迁移能力。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.06969 2026-05-12 cs.CV 79%

Bringing Multimodal Large Language Models to Infrared-Visible Image Fusion Quality Assessment

将多模态大语言模型引入红外-可见图像融合质量评估

Yuchen Guo, Junli Gong, Yao Lu, Xintong Xu, Yiuming Cheung, Weifeng Su

机构 * Northwestern University(西北大学) Northeastern University(东北大学) University of Washington(华盛顿大学) Hong Kong Baptist University(香港 Baptist大学) Beijing Normal - Hong Kong Baptist University(北京师范大学-香港 Baptist大学)

专题命中 红外-可见光融合 :image fusion(title,abstract);分类 cs.CV

AI总结 本文提出FuScore,利用多模态大语言模型生成连续质量评分,以更精确区分质量相近的融合图像,并结合多维子维度一致性和三重目标函数提升评估性能。

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.27712 2026-05-01 cs.CV cs.CL 79%

Linguistically Informed Multimodal Fusion for Vietnamese Scene-Text Image Captioning: Dataset, Graph Framework, and Phonological Attention

具有语言信息的多模态融合用于越南语场景文本图像描述:数据集、图框架和语音注意力

Nhi Ngoc-Yen Nguyen, Anh-Duc Nguyen, Nghia Hieu Nguyen, Kiet Van Nguyen, Ngan Luu-Thuy Nguyen

机构 * Faculty of Information Science and Engineering(信息科学与工程学院) University of Information Technology(信息技术大学) Vietnam National University(越南国家大学)

专题命中 红外-可见光融合 :multimodal fusion(title,abstract);分类 cs.CV

AI总结 本文提出HSTFG和PhonoSTFG框架,通过图拓扑分析发现跨模态边对场景文本融合有害,并构建首个大规模越南语场景文本描述数据集ViTextCaps,揭示52.8%词汇存在声调符号冲突风险。

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.21324 2026-04-24 cs.CV 79%

Temporal Prototyping and Hierarchical Alignment for Unsupervised Video-based Visible-Infrared Person Re-Identification

时序原型与层次对齐用于无监督的基于视频的可见-红外人员重识别

Zhiyong Li, Wei Jiang, Haojie Liu, Mingyu Wang, Wanchong Xu, Weijie Mao

机构 * College of Control Science and Engineering, Zhejiang University(控制科学与工程学院,浙江大学) School of Computer Science and Technology, Zhejiang University of Water Resources and Electric Power(计算机科学与技术学院,浙江水利电力大学)

专题命中 红外-可见光融合 :visible-infrared(title,abstract);分类 cs.CV

AI总结 本文提出HiTPro框架,通过时序感知特征编码器和层次交叉原型对齐,解决无监督视频基于可见-红外人员重识别问题,实现跨模态一致性与不变性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.08924 2026-04-13 cs.CV 79%

Customized Fusion: A Closed-Loop Dynamic Network for Adaptive Multi-Task-Aware Infrared-Visible Image Fusion

定制融合:一种闭环动态网络用于自适应多任务感知红外-可见图像融合

Zengyi Yang, Yu Liu, Juan Cheng, Zhiqin Zhu, Yafei Zhang, Huafeng Li

专题命中 红外-可见光融合 :image fusion(title,abstract);分类 cs.CV

AI总结 本文提出闭环动态网络CLDyN,通过需求驱动语义补偿模块实现多任务自适应的图像融合,实验表明其在保持高质量融合的同时具备强多任务适应性。

Comments This paper has been accepted by CVPR 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.03745 2026-04-10 cs.CV 79%

Dual-level Modality Debiasing Learning for Unsupervised Visible-Infrared Person Re-Identification

双层模态去偏学习用于无监督可见-红外人重识别

Jiaze Li, Yan Lu, Bin Liu, Guojun Yin, Mang Ye

机构 * University of Science and Technology of China(中国科学技术大学) Shanghai Artificial Intelligence Laboratory(上海人工智能实验室) School of Computer Science, Wuhan University(武汉大学计算机学院)

专题命中 红外-可见光融合 :visible-infrared(title,abstract);分类 cs.CV

AI总结 本文提出双层模态去偏学习框架,通过模型和优化层面的去偏策略解决模态偏置问题,提升无监督可见-红外人重识别的性能。

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.01900 2026-04-03 cs.CV 79%

FTPFusion: Frequency-Aware Infrared and Visible Video Fusion with Temporal Perturbation

FTPFusion:基于时序扰动的频率感知红外与可见视频融合

Xilai Li, Chusheng Fang, Xiaosong Li

机构 * Foshan University(佛山大学)

专题命中 红外-可见光融合 :infrared and visible(title,abstract);分类 cs.CV

AI总结 本文提出FTPFusion方法,通过时序扰动和稀疏跨模态交互实现红外与可见视频融合,提升时序稳定性和空间细节保留。

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.08018 2026-04-02 cs.CV 79%

Missing No More: Dictionary-Guided Cross-Modal Image Fusion under Missing Infrared

不再缺失:字典引导的跨模态图像融合在红外缺失情况下的应用

Yafei Zhang, Meng Ma, Huafeng Li, Yu Liu

机构 * Faculty of Information Engineering and Automation, Kunming University of Science and Technology(昆明理工大学信息工程与自动化学院) Department of Biomedical Engineering, Hefei University of Technology(合肥工业大学生物医学工程系)

专题命中 红外-可见光融合 :image fusion(title,abstract);分类 cs.CV

AI总结 本文提出了一种基于共享卷积字典的字典引导框架,解决红外缺失时的跨模态图像融合问题,通过联合字典学习、视觉引导红外推断和自适应融合方法提升感知质量和下游检测性能。

Comments This paper has been accepted by CVPR 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.28414 2026-03-31 cs.CV 79%

Unified Restoration-Perception Learning: Maritime Infrared-Visible Image Fusion and Segmentation

统一的恢复-感知学习:近岸红外-可见图像融合与分割

Weichao Cai, Weiliang Huang, Biao Xue, Chao Huang, Fei Yuan, Bob Zhang

机构 * Laboratory of Underwater Acoustic Communication and Marine Information Technology, Ministry of Education, Xiamen University(厦门大学水声通信与海洋信息技术教育部重点实验室) PAMI Research Group, Department of Computer and Information Science, University of Macau(澳门大学计算机与信息科学系PAMI研究组) School of Cyber Science and Technology, Shenzhen Campus of Sun Yat-sen University(中山大学深圳校区网络空间安全学院)

专题命中 红外-可见光融合 :image fusion(title);multimodal fusion(abstract);分类 cs.CV

AI总结 本文提出IVMSD数据集和MCLF框架,通过FSEC、SVCA和跨模态注意力机制实现海洋场景的图像恢复、多模态融合和语义分割,提升复杂海洋环境下的鲁棒性和感知质量。

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.23508 2026-03-23 cs.CV 79%

Hyperbolic Cycle Alignment for Infrared-Visible Image Fusion

双曲循环对齐用于红外-可见图像融合

Timing Li, Bing Cao, Jiahe Feng, Haifang Cao, Qinghau Hu, Pengfei Zhu

机构 * College of Intelligence and Computing(智能与计算学院)

专题命中 红外-可见光融合 :image fusion(title,abstract);分类 cs.CV

AI总结 本文提出基于双曲空间的双曲循环对齐网络,通过双路径交叉模态循环对齐框架和双曲层次对比对齐模块,实现更有效的多模态图像对齐与融合。

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.16165 2026-03-18 cs.CV cs.AI 79%

Homogeneous and Heterogeneous Consistency progressive Re-ranking for Visible-Infrared Person Re-identification

同质与异质一致性渐进重排序用于可见-红外人重识别

Yiming Wang

专题命中 红外-可见光融合 :visible-infrared(title,abstract);分类 cs.CV

AI总结 本文提出HHCR方法,通过同质和异质一致性重排序解决跨模态人重识别中的模态差异问题,实验表明其方法具有泛化能力并达到最优性能。

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.14243 2026-03-17 cs.CV 79%

BIT: Matching-based Bi-directional Interaction Transformation Network for Visible-Infrared Person Re-Identification

BIT:基于匹配的双向交互转换网络用于可见-红外人重识别

Haoxuan Xu, Guanglin Niu

专题命中 红外-可见光融合 :visible-infrared(title,abstract);分类 cs.CV

AI总结 本文提出BIT网络,通过显式建模可见与红外图像对的交互,解决VI-ReID中模态差异大和分布偏移的问题,实验表明其在重识别任务中表现优异。

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.08208 2026-03-10 cs.CV cs.AI 79%

Alignment-Aware and Reliability-Gated Multimodal Fusion for Unmanned Aerial Vehicle Detection Across Heterogeneous Thermal-Visual Sensors

具有对齐意识和可靠性门控的多模态融合用于跨异质热视觉传感器的无人机检测

Ishrat Jahan, Molla E Majid, M Murugappan, Muhammad E. H. Chowdhury, N. B. Prakash, Saad Bin Abul Kashem, Balamurugan Balusamy, Amith Khandakar

专题命中 红外-可见光融合 :multimodal fusion(title);image fusion(abstract);分类 cs.CV

AI总结 本研究提出RGIF和RGMAF两种融合策略,通过注册意识和可靠性门控提升跨异质热视觉传感器的无人机检测性能。

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.20146 2025-12-29 cs.CV 79%

AlignFreeNet: Is Cross-Modal Pre-Alignment Necessary? An End-to-End Alignment-Free Lightweight Network for Visible-Infrared Object Detection

AlignFreeNet: 跨模态预对齐是否必要?一种端到端无对齐的轻量级网络用于可见-红外目标检测

Dingkun Zhu, Haote Zhang, Lipeng Gu, Wuzhou Quan, Fu Lee Wang, Honghui Fan, Jiali Tang, Haoran Xie, Xiaoping Zhang, Mingqiang Wei

机构 * School of Computer Science, Jiangsu University of Technology(江苏科技大学计算机科学学院) School of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics(南京航空航天大学计算机科学与技术学院) School of Science and Technology, Hong Kong Metropolitan University(香港都会大学科技学院) School of Data Science, Lingnan University(岭南大学数据科学学院) Tsinghua Shenzhen International Graduate School, Tsinghua University(清华大学深圳国际研究生院)

专题命中 红外-可见光融合 :visible-infrared(title,abstract);分类 cs.CV

AI总结 AlignFreeNet通过无对齐融合范式,提出VCC和FCF模块,有效缓解可见-红外目标检测中的跨模态错位问题,实现端到端轻量级网络的高鲁棒性与泛化能力。

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.07760 2025-12-09 cs.CV 79%

Modality-Aware Bias Mitigation and Invariance Learning for Unsupervised Visible-Infrared Person Re-Identification

模态感知的偏见缓解与不变性学习用于无监督的可见-红外人重识别

Menglin Wang, Xiaojin Gong, Jiachen Li, Genlin Ji

专题命中 红外-可见光融合 :visible-infrared(title,abstract);分类 cs.CV

AI总结 本文提出模态感知的偏见缓解与不变性学习方法,通过改进的Jaccard距离和分割与对比策略,在无监督可见-红外人重识别中实现更可靠的跨模态关联和判别性表示学习。

Comments Accepted to AAAI 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.04522 2025-12-05 cs.CV 79%

Identity Clue Refinement and Enhancement for Visible-Infrared Person Re-Identification

身份线索细化与增强用于可见-红外人再识别

Guoqing Zhang, Zhun Wang, Hairui Wang, Zhonglin Ye, Yuhui Zheng

机构 * School of Computer Science, Nanjing University of Information Science and Technology(南京信息工程大学计算机学院) Key Laboratory of Social Computing and Cognitive Intelligence (Dalian University of Technology), Ministry of Education(社会计算与认知智能重点实验室(大连理工大学)) State Key Laboratory of Tibetan Intelligent Information Processing and Application, Qinghai Normal University(藏语智能信息处理与应用国家重点实验室(青海师范大学))

专题命中 红外-可见光融合 :visible-infrared(title,abstract);分类 cs.CV

AI总结 本文提出ICRE网络,通过细化和增强身份线索来提升可见-红外人再识别的性能。

Comments 14 pages, 7 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.16184 2025-11-21 cs.CV 79%

Domain-Shared Learning and Gradual Alignment for Unsupervised Domain Adaptation Visible-Infrared Person Re-Identification

领域共享学习与渐进对齐用于无监督领域适应的可见-红外人员重识别

Nianchang Huang, Yi Xu, Ruida Xi, Ruida Xi, Qiang Zhang

机构 * State Key Laboratory of Electromechanical Integrated Manufacturing of High-Performance Electronic Equipments, Xidian University, Xi’an, Shaanxi 710071, China(高性能电子装备机电一体化制造国家重点实验室,西安电子科技大学,陕西西安710071,中国) Center for Complex Systems, School of Mechano-Electronic Engineering, Xidian University, Xi’an, Shaanxi 710071, China(复杂系统中心,机电工程学院,西安电子科技大学,陕西西安710071,中国)

专题命中 红外-可见光融合 :visible-infrared(title,abstract);分类 cs.CV

AI总结 本文提出DSLGA模型,通过领域共享学习和渐进对齐策略解决可见-红外人员重识别中的领域间和领域内模态差异问题,提升无监督领域适应性能。

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.15016 2025-11-20 cs.CV 79%

CKDA: Cross-modality Knowledge Disentanglement and Alignment for Visible-Infrared Lifelong Person Re-identification

Zhenyu Cui, Jiahuan Zhou, Yuxin Peng

机构 * Zhenyu Cui, Jiahuan Zhou, Yuxin Peng(作者)

专题命中 红外-可见光融合 :visible-infrared(title,abstract);分类 cs.CV

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.10046 2025-11-17 cs.CV 79%

FreDFT: Frequency Domain Fusion Transformer for Visible-Infrared Object Detection

Wencong Wu, Xiuwei Zhang, Hanlin Yin, Shun Dai, Hongxi Zhang, Yanning Zhang

机构 * School of Computer Science, Northwestern Polytechnical University(西北工业大学计算机学院)

专题命中 红外-可见光融合 :visible-infrared(title,abstract);分类 cs.CV

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.04281 2025-11-07 cs.CV 79%

DINOv2 Driven Gait Representation Learning for Video-Based Visible-Infrared Person Re-identification

Yujie Yang, Shuang Li, Jun Ye, Neng Dong, Fan Li, Huafeng Li

机构 * Kunming University of Science and Technology(昆明理工大学) Chongqing University of Post and Telecommunications(重庆邮电大学) China University of Mining Technology(中国矿业大学) Nanjing University of Science and Technology(南京理工大学)

专题命中 红外-可见光融合 :visible-infrared(title,abstract);分类 cs.CV

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.02685 2025-11-05 cs.CV 79%

Modality-Transition Representation Learning for Visible-Infrared Person Re-Identification

Chao Yuan, Zanwu Liu, Guiwei Zhang, Haoxuan Xu, Yujian Zhao, Guanglin Niu, Bo Li

机构 * Beihang University(北航大学)

专题命中 红外-可见光融合 :visible-infrared(title,abstract);分类 cs.CV

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.11587 2025-09-16 cs.CV cs.AI 79%

Hierarchical Identity Learning for Unsupervised Visible-Infrared Person Re-Identification

Haonan Shi, Yubin Wang, De Cheng, Lingfeng He, Nannan Wang, Xinbo Gao

机构 * IEEE Publication Technology Department(IEEE出版技术部门) State Key Laboratory of Integrated Services Networks, School of Telecommunications Engineering, Xidian University(信息服务网络国家重点实验室,电信工程学院,西安电子科技大学) Department of Computer Science and Technology, Tongji University(计算机科学与技术系,同济大学)

专题命中 红外-可见光融合 :visible-infrared(title,abstract);分类 cs.CV

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.12232 2025-08-29 cs.CV 79%

L2RW+: A Comprehensive Benchmark Towards Privacy-Preserved Visible-Infrared Person Re-Identification

Yan Jiang, Hao Yu, Mengting Wei, Zhaodong Sun, Haoyu Chen, Xu Cheng, Guoying Zhao

机构 * Center for Machine Vision and Signal Analysis, University of Oulu(机器视觉与信号分析中心,奥卢大学) University of Oulu(奥卢大学) School of Computer Science, Nanjing University of Information Science and Technology(信息科学技术大学计算机学院) Nanjing University of Information Science and Technology(信息科学技术大学)

专题命中 红外-可见光融合 :visible-infrared(title,abstract);分类 cs.CV

Comments Extended Version of L2RW. We extend it from image to video data

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.09514 2025-08-08 cs.CV 79%

CM-Diff: A Single Generative Network for Bidirectional Cross-Modality Translation Diffusion Model Between Infrared and Visible Images

Bin Hu, Chenqiang Gao, Shurui Liu, Junjie Guo, Fang Chen, Fangcen Liu, Junwei Han

专题命中 红外-可见光融合 :infrared and visible(title,abstract);分类 cs.CV

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.10888 2025-07-21 cs.CV cs.AI 79%

CDUPatch: Color-Driven Universal Adversarial Patch Attack for Dual-Modal Visible-Infrared Detectors

Jiahuan Long, Wen Yao, Tingsong Jiang, Chao Ma

机构 * Chinese Academy of Military Science(中国军事科学院) Shanghai Jiao Tong University(上海交通大学)

专题命中 红外-可见光融合 :visible-infrared(title,abstract);分类 cs.CV

Comments Accepted by ACMMM 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.12942 2025-07-18 cs.CV 79%

Weakly Supervised Visible-Infrared Person Re-Identification via Heterogeneous Expert Collaborative Consistency Learning

Yafei Zhang, Lingqi Kong, Huafeng Li, Jie Wen

机构 * Faculty of Information Engineering and Automation, Kunming University of Science and Technology(昆明理工大学信息工程与自动化学院) School of Computer Science and Technology, Harbin Institute of Technology(哈尔滨工业大学计算机科学与技术学院)

专题命中 红外-可见光融合 :visible-infrared(title,abstract);分类 cs.CV

Comments Accepted by ICCV 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.01912 2025-07-03 cs.CV 79%

3D Reconstruction and Information Fusion between Dormant and Canopy Seasons in Commercial Orchards Using Deep Learning and Fast GICP

Ranjan Sapkota, Zhichao Meng, Martin Churuvija, Xiaoqiang Du, Zenghong Ma, Manoj Karkee

机构 * organization= Department of Biological \& Environmental Engineering, Cornell University , addressline= Riley-Robb Hall, 106, 111 Wing Dr , city= Ithaca , postcode= 14850 , state= New York , country= USA organization= School of Mechanical Engineering, Zhejiang Sci-Tech University , addressline= Hangzhou 310018 , city= Hangzhou , country= China

专题命中 红外-可见光融合 :information fusion(title,abstract);分类 cs.CV

Comments 17 pages, 4 tables, 11 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.06665 2025-05-13 cs.CV 79%

MultiTaskVIF: Segmentation-oriented visible and infrared image fusion via multi-task learning

Zixian Zhao, Andrew Howes, Xingchen Zhang

机构 * The Fusion Intelligence Laboratory, Department of Computer Science, University of Exeter(埃克塞特大学计算机科学系融合智能实验室)

专题命中 红外-可见光融合 :image fusion(title,abstract);分类 cs.CV

详情

展开后加载摘要…

URL PDF HTML 收藏