EUVIMEDEUVIMED entdecken
Crossref

Disentangle to Fuse: Toward Content Preservation and Cross-Modality Consistency for Multi-Modality Image Fusion

Xinran Qin, Yuning Cui, Shangquan Sun, Ruoyu Chen, Wenqi Ren, Alois Knoll, Xiaochun Cao

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.

AbstractBibliografische AngabenZitierenVerwandte Studien

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}
}
Kostenlos starten →