Linfeng Tang
Postdoctoral Researcher at Wuhan University.
Computer Vision | Image Fusion | Image Enhancement
I am Linfeng Tang (唐霖峰), a Postdoctoral Researcher at Wuhan University, advised by Prof. Jiayi Ma.
I received my Ph.D. from the Electronic Information School, Wuhan University, in December 2025, and my B.E. from Central South University in 2020. My research focuses on multi-modal image fusion, video fusion, low-light enhancement, restoration, and semantics-aware perception. I was named to Stanford University's World's Top 2% Scientists list in 2025 and received two Best Paper Awards: the Hsue-shen Tsien Paper Award (IEEE/CAA JAS, 2023) and the Information Fusion Best Paper Award (2024).
My publication record includes 6 ESI Hot Papers (top 0.1%) and 8 ESI Highly Cited Papers (top 1%).
Research Focus
Multi-modal Fusion
Infrared-visible image fusion, video fusion, controllable fusion, and registration-fusion joint modeling.
Enhancement and Restoration
Low-light enhancement, degradation-aware restoration, and diffusion-based image recovery.
Task-driven Perception
Semantic guidance, language-vision priors, and image fusion models designed for downstream high-level vision tasks.
Projects
National Natural Science Foundation of China
Youth Science Fund (Category C)
Controllable and robust multimodal image fusion through cross-level vision-semantic collaboration
China Postdoctoral Science Foundation
National-funded Postdoctoral Researcher Program (Grade B)
Robust fusion and trustworthy interpretation of multi-source heterogeneous remote-sensing imagery through perception-cognition collaboration
China Postdoctoral Science Foundation
79th General Grant
Collaborative perception theory and methods for multi-source image fusion in open-world scenarios
Representative Works
Mask-DiFuser
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2026
Unifies multiple unsupervised image-fusion tasks through masked diffusion modeling.
C2RF
International Journal of Computer Vision (IJCV), 2025
ControlFusion
Advances in Neural Information Processing Systems (NeurIPS), 2025
VideoFusion
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026
SwinFusion
IEEE/CAA Journal of Automatica Sinica, 2022
Models cross-domain long-range dependencies with a Swin Transformer for general image fusion.
SeAFusion
Information Fusion, 2022
Introduces semantic awareness and high-level task feedback into real-time infrared-visible fusion.
PIAFusion
Information Fusion, 2022
Progressively fuses infrared and visible information according to illumination conditions.
SuperFusion
IEEE/CAA Journal of Automatica Sinica, 2022
Jointly addresses image registration and semantics-aware fusion for spatially misaligned inputs.
DIVFusion
Information Fusion, 2023
Suppresses dark regions and improves detail visibility in low-light infrared-visible fusion.
PSFusion
Information Fusion, 2023
Connects low-level fusion quality with high-level tasks through semantic injection and scene fidelity.
STDFusionNet
IEEE Transactions on Instrumentation and Measurement, 2021
Uses salient-target detection to preserve critical thermal targets and structural information.
Deep Learning-based Image Fusion: A Survey
Journal of Image and Graphics, 2023
Citation counts on this page are synchronized daily from my personal Google Scholar profile. The live profile remains available on Google Scholar.
Academic Service
I serve as a reviewer for TPAMI, TIP, TNNLS, TMM, TCSVT, TII, TGRS, TITS, TSMC, TASE, JSAC, JAS, IoTJ, IJCV, Information Fusion, PR, CVPR, NeurIPS, ECCV, AAAI, IJCAI, and ACM MM. A fuller list is available on the Services page.
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 | 获 中国博士后科学基金第 79 批面上资助。 |
| Jul 17, 2026 | 获 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
- IEEE TPAMI
- Inf. Fusion
Image fusion in the loop of high-level vision tasks: A semantic-aware real-time infrared and visible image fusion networkInformation Fusion, 2022Semantic-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 - IEEE/CAA JAS
SwinFusion: Cross-domain Long-range Learning for General Image Fusion via Swin TransformerIEEE/CAA Journal of Automatica Sinica, 2022Cross-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 - IEEE/CAA JAS
- Inf. Fusion
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 fidelityInformation Fusion, 2023Progressive semantic injection and scene fidelity for task-oriented fusion; ESI Hot Paper; ESI Highly Cited Paper Google Scholar citations
