计算机视觉 | 图像融合 | 图像增强

我是 唐霖峰,现为武汉大学机器人学院博士后,合作导师为 马佳义教授

我于 2025 年 12 月获武汉大学电子信息学院博士学位,于 2020 年获中南大学学士学位。我的研究方向主要包括多模态图像融合、视频融合、低照度图像增强、图像恢复,以及语义感知建模。2025 年入选 斯坦福大学发布的全球前 2% 顶尖科学家榜单,并获得两项最佳论文奖:钱学森论文奖(IEEE/CAA JAS,2023)和 Information Fusion 最佳论文奖(2024)。

目前共有 6 篇 ESI 热点论文(前 0.1%)和 8 篇 ESI 高被引论文(前 1%)。

17 篇一作论文
8,311 Google Scholar citations · h-index 22
2 最佳论文奖
6 / 8 ESI 热点 / 高被引论文

研究方向

多模图像融合

红外-可见光图像融合、视频融合、可控融合,以及配准与融合联合建模。

图像增强与恢复

低照度图像增强、退化感知恢复,以及基于扩散模型的图像恢复方法。

任务驱动感知

语义引导、语言-视觉先验,以及面向检测、分割等高层视觉任务的图像融合模型。

科研项目

中国博士后科学基金会

国家资助博士后研究人员计划B档

感知-认知协同的多源异构遥感影像鲁棒融合与可信解译方法研究

中国博士后科学基金会

第 79 批面上资助

面向开放场景的多源图像融合感知协同理论及方法研究

代表性工作

本页展示的引用数据已根据本人 Google Scholar 主页于 2026 年 7 月 18 日更新,实时数据请以 Google Scholar 为准。

学术服务

目前担任 TPAMI、TIP、TNNLS、TMM、TCSVT、TII、TGRS、TITS、TSMC、TASE、JSAC、JAS、IoTJ、IJCV、Information Fusion、PR,以及 CVPR、NeurIPS、ECCV、AAAI、IJCAI、ACM MM 等期刊和会议审稿人。完整列表见 学术服务 页面。

News

Aug 26, 2026 获批 国家自然科学基金青年科学基金项目(C类)
Jul 24, 2026 中国博士后科学基金第 79 批面上资助
Jul 17, 2026 2026 年度国家资助博士后研究人员计划 B 档资助
Feb 20, 2026 Our paper “VideoFusion” accepted by CVPR 2026! [Paper][Code]
Dec 26, 2025 我们的综述《基于深度学习的图像融合方法综述》荣获 中国图象图形学报 2020-2024 优秀论文

Selected Publications

  1. CVPR
    VideoFusion.jpg
    VideoFusion: A Spatio-Temporal Collaborative Network for Multi-modal Video Fusion and Restoration
    Linfeng Tang, Yeda Wang, Meiqi Gong, and 7 more authors
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026
  2. IEEE TPAMI
    Mask-DiFuser.jpg
    Mask-DiFuser: A Masked Diffusion Model for Unified Unsupervised Image Fusion
    Linfeng Tang, Chunyu Li, and Jiayi Ma
    IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2026
    Masked diffusion modeling that unifies multiple unsupervised image-fusion tasks; ESI Highly Cited Paper Google Scholar citations
  3. NeurIPS
    ControlFusion.jpg
    ControlFusion: A Controllable Image Fusion Framework with Language-Vision Degradation Prompts
    Linfeng Tang, Yeda Wang, Zhanchuan Cai, and 2 more authors
    In Advances in Neural Information Processing Systems (NeurIPS), 2025
    Oral Presentation
  4. IJCV
    C2RF.jpg
    C2RF: Bridging Multi-modal Image Registration and Fusion via Commonality Mining and Contrastive Learning
    Linfeng Tang, Qinglong Yan, Xinyu Xiang, and 2 more authors
    International Journal of Computer Vision (IJCV), 2025
  5. ACM MM
    DRMF.jpg
    DRMF: Degradation-Robust Multi-Modal Image Fusion via Composable Diffusion Prior
    Linfeng Tang, Yuxin Deng, Xunpeng Yi, and 3 more authors
    In Proceedings of the ACM International Conference on Multimedia (ACM MM), 2024
  6. Inf. Fusion
    SeAFusion.jpg
    Image fusion in the loop of high-level vision tasks: A semantic-aware real-time infrared and visible image fusion network
    Linfeng Tang, Jiteng Yuan, and Jiayi Ma
    Information Fusion, 2022
    Semantic-aware real-time infrared-visible fusion with high-level task feedback; Information Fusion Best Paper Award 2024; ESI Hot Paper; ESI Highly Cited Paper Google Scholar citations
  7. IEEE/CAA JAS
    SwinFusion.jpg
    SwinFusion: Cross-domain Long-range Learning for General Image Fusion via Swin Transformer
    Jiayi Ma, Linfeng Tang, Fan Fan, and 3 more authors
    IEEE/CAA Journal of Automatica Sinica, 2022
    Cross-domain long-range modeling with a Swin Transformer for general image fusion; IEEE/CAA JAS 2023 Best Paper Award, sole annual winner; ESI Hot Paper; ESI Highly Cited Paper Google Scholar citations
  8. Inf. Fusion
    PIAFusion.jpg
    PIAFusion: A progressive infrared and visible image fusion network based on illumination aware
    Linfeng Tang, Jiteng Yuan, Hao Zhang, and 2 more authors
    Information Fusion, 2022
    Progressive infrared-visible fusion guided by illumination conditions; ESI Hot Paper; ESI Highly Cited Paper Google Scholar citations
  9. IEEE/CAA JAS
    SuperFusion.jpg
    SuperFusion: A Versatile Image Registration and Fusion Network with Semantic Awareness
    Linfeng Tang, Yuxin Deng, Yong Ma, and 2 more authors
    IEEE/CAA Journal of Automatica Sinica, 2022
    Joint image registration and semantics-aware fusion for spatially misaligned inputs; ESI Hot Paper; ESI Highly Cited Paper Google Scholar citations
  10. Inf. Fusion
    DIVFusion.jpg
    DIVFusion: Darkness-free infrared and visible image fusion
    Linfeng Tang, Xinyu Xiang, Hao Zhang, and 2 more authors
    Information Fusion, 2023
    Darkness-free infrared-visible fusion for low-light scenes; ESI Hot Paper; ESI Highly Cited Paper Google Scholar citations
  11. Inf. Fusion
    PSFusion.jpg
    Rethinking the necessity of image fusion in high-level vision tasks: A practical infrared and visible image fusion network based on progressive semantic injection and scene fidelity
    Linfeng Tang, Hao Zhang, Han Xu, and 1 more author
    Information Fusion, 2023
    Progressive semantic injection and scene fidelity for task-oriented fusion; ESI Hot Paper; ESI Highly Cited Paper Google Scholar citations
  12. IEEE TIM
    STDFusionNet.jpg
    STDFusionNet: An Infrared and Visible Image Fusion Network Based on Salient Target Detection
    Jiayi Ma, Linfeng Tang, Meilong Xu, and 2 more authors
    IEEE Transactions on Instrumentation and Measurement, 2021
    Salient-target detection for preserving critical thermal targets and structures; ESI Highly Cited Paper Google Scholar citations
  13. JIG
    Survey.jpg
    基于深度学习的图像融合方法综述
    唐霖峰, 张浩, 徐涵, and 1 more author
    中国图象图形学报, 2024
    空天信息科技期刊高影响力论文, 中国图象图形学报 2020-2024 优秀论文, 中国图象图形学报 2024 年度优秀论文, 中国图象图形学报优秀成果报告 Google Scholar citations