Customized Fusion: A Closed-Loop Dynamic Network for Adaptive Multi-Task-Aware Infrared-Visible Image Fusion
2026-04-10 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors created a new system called CLDyN to combine infrared and visible images so it can better support different tasks without needing to be retrained each time. Their method uses a feedback loop that helps the system understand what each task needs and adjusts the image fusion accordingly. They introduced special components to customize the fusion process for each task and a system to reward or penalize adjustments based on how well the tasks perform. Tests show their system keeps good image quality while working well across multiple tasks.
infrared-visible image fusionclosed-loop optimizationsemantic transmissionRequirement-driven Semantic CompensationBasis Vector BankArchitecture-Adaptive Semantic Injectionreward-penalty strategymulti-task adaptability
Authors
Zengyi Yang, Yu Liu, Juan Cheng, Zhiqin Zhu, Yafei Zhang, Huafeng Li
Abstract
Infrared-visible image fusion aims to integrate complementary information for robust visual understanding, but existing fusion methods struggle with simultaneously adapting to multiple downstream tasks. To address this issue, we propose a Closed-Loop Dynamic Network (CLDyN) that can adaptively respond to the semantic requirements of diverse downstream tasks for task-customized image fusion. Specifically, CLDyN introduces a closed-loop optimization mechanism that establishes a semantic transmission chain to achieve explicit feedback from downstream tasks to the fusion network through a Requirement-driven Semantic Compensation (RSC) module. The RSC module leverages a Basis Vector Bank (BVB) and an Architecture-Adaptive Semantic Injection (A2SI) block to customize the network architecture according to task requirements, thereby enabling task-specific semantic compensation and allowing the fusion network to actively adapt to diverse tasks without retraining. To promote semantic compensation, a reward-penalty strategy is introduced to reward or penalize the RSC module based on task performance variations. Experiments on the M3FD, FMB, and VT5000 datasets demonstrate that CLDyN not only maintains high fusion quality but also exhibits strong multi-task adaptability. The code is available at https://github.com/YR0211/CLDyN.