TY - GEN
T1 - P2Fusion
T2 - 19th European Conference on Computer Vision, ECCV 2026
AU - Shi, Yi
AU - Xie, Huichao
AU - Wang, Yuqing
AU - Wang, Mingyu
AU - Yang, Kaihui
AU - Liu, Yu
AU - Lu, Ruitao
AU - Li, Lizhe
AU - Han, Junwei
AU - Zhang, Dingwen
N1 - Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.
PY - 2026
Y1 - 2026
N2 - 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.
AB - 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.
KW - Infrared-visible image fusion
KW - Knowledge distillation
KW - Multimodal perception
KW - Prompt-based learning
UR - https://www.scopus.com/pages/publications/105052050383
U2 - 10.1007/978-3-032-37447-9_30
DO - 10.1007/978-3-032-37447-9_30
M3 - 会议稿件
AN - SCOPUS:105052050383
SN - 9783032374462
T3 - Lecture Notes in Computer Science
SP - 542
EP - 561
BT - Computer Vision – ECCV 2026 - 19th European Conference, Malmö, Sweden, September 8–12, 2026, Proceedings
A2 - Favaro, Paolo
A2 - Kukelova, Zuzana
A2 - Maki, Atsuto
A2 - Rohrbach, Anna
A2 - Schindler, Konrad
A2 - Tombari, Federico
PB - Springer Science and Business Media Deutschland GmbH
Y2 - 8 September 2026 through 12 September 2026
ER -