---
title: "SpeciFuse: Learning Degradation-Type Specificity for Robust Infrared and Visible Image Fusion Under Composite Degradations"
authors:
  - "Xuan Li"
  - "Zhaoming Feng"
  - "Xiang Yuan"
  - "Huabing Zhou"
  - "Jiayi Ma"
doi: "10.24963/ijcai.2026/155"
url: "https://ijcai.org/proceedings/2026/155"
pdf: "https://ijcai.org/proceedings/2026/0155.pdf"
venue: "Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence"
year: 2026
pages: "1388-1396"
track: "Main Track"
keywords:
  - "Computer Vision: Representation learning"
  - "Computer Vision: Machine learning for vision"
  - "Computer Vision: Multimodal learning"
---

# SpeciFuse: Learning Degradation-Type Specificity for Robust Infrared and Visible Image Fusion Under Composite Degradations

Xuan Li, Zhaoming Feng, Xiang Yuan, Huabing Zhou, Jiayi Ma

*Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence*, pages 1388-1396. DOI: [10.24963/ijcai.2026/155](https://doi.org/10.24963/ijcai.2026/155)

## Abstract

Existing degradation-resistant infrared-visible image fusion methods struggle to effectively handle composite degradations, where multiple degradation types exhibit intricate coupling and mutual interference. To address this challenge, we propose SpeciFuse, an infrared-visible image fusion network that learns degradation-specific representations. By explicitly modeling the specificity of individual degradations through a siamese architecture trained on single-degradation data, our method effectively addresses the conflicts arising from multiple degradations, thereby achieving robust fusion performance that generalizes to diverse composite degradation scenarios. In SpeciFuse, a degradation-type specificity decoupling module is designed to disentangle the feature representations by attenuating their redundant correlations in a latent space. It minimizes off-diagonal elements to enforce independence among the encodings of distinct degradation types, while preserving dominant diagonal elements to maintain shared content information. Furthermore, a degradation-aware gated fusion module leverages these decoupled features to dynamically modulate cross-modal fusion across both channel and spatial dimensions. This facilitates a degradation-conditional fusion process that adaptively suppresses degradation artifacts while preserving beneficial information across varying conditions. In extensive comparisons with state-of-the-art methods, SpeciFuse demonstrates more robust performance under diverse composite degradations. The code is available at https://github.com/xbsj-cool/SpeciFuse.