The qualitative comparisons on TNO 02.png.

<div><p>In response to the limitations of current infrared and visible light image fusion algorithms—namely insufficient feature extraction, loss of detailed texture information, underutilization of differential and shared information, and the high number of model parameters—this paper p...

وصف كامل

محفوظ في:

التفاصيل البيبلوغرافية
المؤلف الرئيسي:	Xicheng Sun (2104468) (author)
مؤلفون آخرون:	Fu Lv (17708560) (author), Yongan Feng (7345193) (author), Xu Zhang (49484) (author)
منشور في:	2025
الموضوعات:	Space Science Environmental Sciences not elsewhere classified Biological Sciences not elsewhere classified Mathematical Sciences not elsewhere classified Information Systems not elsewhere classified reducing network parameters objective evaluation results model parameters — minimizing computational complexity experimental results demonstrate dimensional fusion branch depthwise separable convolutions proposed method outperforms proposed method introduces incorporating group convolution detailed texture information level attention module demonstrates good performance attention fusion module branch feature interaction scale group convolution div >< p scale information interaction shared information proposed algorithm gs convolution superior performance local attention attention mechanism scale infrared tested extensively shared features seven others public datasets paper proposes multimodal images integrating edge high number dataset confirm
الوسوم:	إضافة وسم لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!

The qualitative comparisons on TNO 02.png.

مواد مشابهة