Semantic-Relation Transformer for Visible and Infrared Fused Image Quality Assessment

Zhihao Chang, Shuyuan Yang, Zhixi Feng, Quanwei Gao, Shengzhe Wang, Yuyong Cui

Abstract: Highlights•A subjective benchmark dataset called Visible and Infrared fuSed qualiTy Assessment is built.•The subjective fused image quality assessment specification is formulated.•A new Semantic Relation Transformer is proposed for fused image quality assessment.•Fusion quality is assessed in SRT through semantic embedding and relation knowledge.•MHSE blocks are advanced to explore the correlation between source and fused images.