Disentangle to Fuse: Toward Content Preservation and Cross-Modality Consistency for Multi-Modality Image Fusion
IEEE Transactions on Image Processing · 2026 · 35 · 1756-1770
DOI: 10.1109/tip.2026.3657183 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Image Processing, 2026. Verfasst von Xinran Qin und 6 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 88 Literaturangaben. Gefördert von: Shenzhen Science and Technology Program, National Natural Science Foundation of China, Open Fund of Key Laboratory of the Ministry of Education on Artificial Intelligence in Equipment.
Abstract (Originalsprache)
Multi-modal image fusion (MMIF) aims to integrate complementary information from heterogeneous sensor modalities. However, substantial cross-modality discrepancies hinder joint scene representation and lead to semantic degradation in the fused output. To address this limitation, we propose C2MFuse, a novel framework designed to preserve content while ensuring cross-modality consistency. To the best of our knowledge, this is the first MMIF approach to explicitly disentangle style and content representations across modalities for image fusion. C2MFuse introduces a content-preserving style normalization mechanism that suppresses modality-specific variations while maintaining the underlying scene structure. The normalized features are then progressively aggregated to enhance fine-grained details and improve content completeness. In light of the lack of ground truth and the inherent ambiguity of the fused distribution, we further align the fused representation with a well-defined source modality, thereby enhancing semantic consistency and reducing distributional uncertainty. Additionally, we introduce an adaptive consistency loss with learnable transformation, which provides dynamic, modality-aware supervision by enforcing global consistency across heterogeneous inputs. Extensive experiments on five datasets across three representative MMIF tasks demonstrate that C2MFuse achieves efficient and high-quality fusion, surpasses existing methods, and generalizes effectively to downstream visual applications.
Förderung
- Shenzhen Science and Technology Program
- National Natural Science Foundation of China
- Open Fund of Key Laboratory of the Ministry of Education on Artificial Intelligence in Equipment
Zitieren
APA
Qin, X., Cui, Y., Sun, S., Chen, R., Ren, W., Knoll, A., & Cao, X. (2026). Disentangle to Fuse: Toward Content Preservation and Cross-Modality Consistency for Multi-Modality Image Fusion. IEEE Transactions on Image Processing, 35, 1756-1770. https://doi.org/10.1109/tip.2026.3657183
Vancouver
Qin X, Cui Y, Sun S, Chen R, Ren W, Knoll A, et al. Disentangle to Fuse: Toward Content Preservation and Cross-Modality Consistency for Multi-Modality Image Fusion. IEEE Transactions on Image Processing. 2026;35:1756-1770. doi:10.1109/tip.2026.3657183
BibTeX
@article{Qin2026,
author = {Qin, Xinran and Cui, Yuning and Sun, Shangquan and Chen, Ruoyu and Ren, Wenqi and Knoll, Alois and Cao, Xiaochun},
title = {Disentangle to Fuse: Toward Content Preservation and Cross-Modality Consistency for Multi-Modality Image Fusion},
journal = {IEEE Transactions on Image Processing},
year = {2026},
volume = {35},
pages = {1756--1770},
doi = {10.1109/tip.2026.3657183}
}
EUVIMED