collaborators

8 papers

cs.CV2025

Coupled Degradation Modeling and Fusion: A VLM-Guided Degradation-Coupled Network for Degradation-Aware Infrared and Visible Image Fusion

Tianpei Zhang, Jufeng Zhao, Yiming Zhu +1

Existing Infrared and Visible Image Fusion (IVIF) methods typically assume high-quality inputs. However, when handing degraded images, these methods heavily rely on manually switch…

cs.CV2025

DDFusion:Degradation-Decoupled Fusion Framework for Robust Infrared and Visible Images Fusion

Tianpei Zhang, Jufeng Zhao, Yiming Zhu +2

Conventional infrared and visible image fusion(IVIF) methods often assume high-quality inputs, neglecting real-world degradations such as low-light and noise, which limits their pr…

cs.CV2025

Dual-Domain Perspective on Degradation-Aware Fusion: A VLM-Guided Robust Infrared and Visible Image Fusion Framework

Tianpei Zhang, Jufeng Zhao, Yiming Zhu +1

Most existing infrared-visible image fusion (IVIF) methods assume high-quality inputs, and therefore struggle to handle dual-source degraded scenarios, typically requiring manual s…

eess.IV2025

Make Both Ends Meet: A Synergistic Optimization Infrared Small Target Detection with Streamlined Computational Overhead

Yuxin Jing, Yuchen Zheng, Jufeng Zhao +2

Infrared small target detection(IRSTD) is widely recognized as a challenging task due to the inherent limitations of infrared imaging, including low signal-to-noise ratios, lack of…

cs.CV2025

FSATFusion: Frequency-Spatial Attention Transformer for Infrared and Visible Image Fusion

Tianpei Zhang, Jufeng Zhao, Yiming Zhu +2

The infrared and visible images fusion (IVIF) is receiving increasing attention from both the research community and industry due to its excellent results in downstream application…

cs.CV2025

WIFE-Fusion:Wavelet-aware Intra-inter Frequency Enhancement for Multi-model Image Fusion

Tianpei Zhang, Jufeng Zhao, Yiming Zhu +1

Multimodal image fusion effectively aggregates information from diverse modalities, with fused images playing a crucial role in vision systems. However, existing methods often negl…