P2Fusion, a prior-guided distillation-based framework that reformulates IVIF via dual intrinsic prompts, distill image-intrinsic priors, thermal saliency and spatial quality, into learnable dynamic regulators, and enables the network to adaptively mediate modal competition through expert specialization.
Abstract
Infrared-visible image fusion (IVIF) is pivotal for multimodal perception, yet reconciling the inherent information disparity between thermal and textural features remains a fundamental challenge. Existing prior-guided methods often rely on static constraints that induce optimization conflicts or utilize extrinsic semantic priors from large-scale foundation models (e.g., CLIP/DINO), which frequently fail to exploit the intrinsic modality characteristics essential for high-fidelity fusion. To address these issues, we propose P2Fusion, a prior-guided distillation-based framework that reformulates IVIF via dual intrinsic prompts. Instead of imposing hard-coded penalties, we distill image-intrinsic priors, thermal saliency and spatial quality, into learnable dynamic regulators. Specifically, a Teach-to-Fuse mechanism provides dual-granularity progressive guidance, coupled with a Gated Dynamic Expert Recalibration (GDER) module for decoupled feature refinement. This design enables the network to adaptively mediate modal competition through expert specialization. Extensive experiments demonstrate that P2Fusion achieves state-of-the-art performance across five mainstream datasets. Notably, our framework demonstrates consistent performance advantages in fusion quality, achieving state-of-the-art results in 14 out of 20 key evaluation metrics across 5 benchmarks. Furthermore, it effectively contributes to the robustness of downstream perception, such as +3.2% mAP on MSRS, +0.5% mAP on M3FD and +0.9% mAP on DroneVehicle for object detection. Our code will be available at https://github.com/YiShi99/P2Fusion
SGPDFuse is proposed, which bridges this gap by mapping inputs into a physics-disentangled structural representation via a Semantic-Physical Parametric Bridge (SPPB) built on pretrained vision foundation models, utilizing the Intrinsic-Variation principle to decouple invariant scene attributes from transient environmen...
Hao-Zheng Wei, Cheng-Jun Jiang, Yu-Tong Guo et al.· 0 citations
This paper proposes a symbiotic evolutionary learning framework for task-adaptive IVIF, termed EvoFuse, which enables a mutual adaptation process where the fusion network and task models are jointly updated under a Pareto-inspired non-degradation criterion.
Jin-Yuan Liu, Bowei Zhang, Ludan Sun et al.· IEEE Transactions on Pattern...· 1 citation
Infrared–visible image fusion aims to combine thermal saliency from infrared imagery with the structural detail preserved in the visible spectrum. In existing fusion methods, the two modalities are fused through fixed channel mixing, the same text embedding is reused across decoder scales, and explicit cross-modal inte...
DARD first extracts image-specific physical priors from the degraded input through a test-time degradation-aware Retinex decomposition, thereby providing reliable structural guidance for zero-shot restoration and injects these priors into reverse diffusion through a timestep-adaptive frequency fusion strategy to balanc...
Wen-Jie Cai, Yuezhe Yang, Jian-Yang Xia et al.· IEEE transactions on circuit...· 0 citations
A Boundary-Guided Dual-Perspective Cross-Modal Fusion Network (BDPNet) is proposed to explicitly preserve shallow geometric structures and decouple deep semantic fusion into macroscopic and microscopic perspectives.
Hu Lin, Zhi-Wei Fu, Xiu-Mei Chen et al.· Remote Sensing· 0 citations
A lightweight end-to-end IVIF network with two complementary refinement modules that achieves the best or tied-best value on three of seven standard fusion-quality metrics on FMB and four of seven on LLVIP, and ablation results further confirm the complementary effects of MSG and DGM.
Wenhua Zhao, Lei Zhong· Applied Sciences· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.