不再缺失：缺失红外条件下的字典引导跨模态图像融合
Missing No More: Dictionary-Guided Cross-Modal Image Fusion under Missing Infrared
把跨模态融合从像素空间生成搬到共享卷积字典的系数域，用「编码-迁移-融合-重建」闭环替代不可控的像素级生成；对做多模态融合、缺失模态补全的研究者，这套字典-系数表示提供了一个可解释、可复用且能接下游检测的替代范式。
原文依据 This encode-transfer-fuse-reconstruct pipeline avoids uncontrolled pixel-space generation while ensuring prior preservation within interpretable dictionary-coefficient representation.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论红外-可见光（IR-VIS）图像融合对感知与安防至关重要，但现有方法大多依赖训练和推理阶段两种模态同时可用。当红外模态缺失时，像素空间的生成式替代结果难以控制，且本质上缺乏可解释性。本文针对缺失红外融合问题，提出一个基于共享卷积字典的、字典引导的系数域框架。该流程包含三个关键组件：（1）联合共享字典表征学习（JSRL）学习一个由红外与可见光两种模态共享的统一且可解释的原子空间；（2）可见光引导的红外推理（VGII）在系数域中将可见光系数迁移为伪红外系数，并以冻结的大语言模型作为弱语义先验执行一步闭环精化；（3）基于表征推理的自适应融合（AFRI）通过窗口注意力与卷积混合，在原子层面融合可见光结构与推断出的红外线索，随后用共享字典进行重建。这一「编码-迁移-融合-重建」流程避免了不受控的像素空间生成，同时在可解释的字典-系数表征内保证了先验的保留。缺失红外设置下的实验表明，该方法在感知质量与下游检测性能上均取得一致提升。据我们所知，这是首个联合学习共享字典并在系数域执行推理-融合以解决缺失红外融合问题的框架。源代码已公开于 https://github.com/harukiv/DCMIF。
英文原文摘要 1647 字符
Infrared-visible (IR-VIS) image fusion is vital for perception and security, yet most methods rely on the availability of both modalities during training and inference. When the infrared modality is absent, pixel-space generative substitutes become hard to control and inherently lack interpretability. We address missing-IR fusion by proposing a dictionary-guided, coefficient-domain framework built upon a shared convolutional dictionary. The pipeline comprises three key components: (1) Joint Shared-dictionary Representation Learning (JSRL) learns a unified and interpretable atom space shared by both IR and VIS modalities; (2) VIS-Guided IR Inference (VGII) transfers VIS coefficients to pseudo-IR coefficients in the coefficient domain and performs a one-step closed-loop refinement guided by a frozen large language model as a weak semantic prior; and (3) Adaptive Fusion via Representation Inference (AFRI) merges VIS structures and inferred IR cues at the atom level through window attention and convolutional mixing, followed by reconstruction with the shared dictionary. This encode-transfer-fuse-reconstruct pipeline avoids uncontrolled pixel-space generation while ensuring prior preservation within interpretable dictionary-coefficient representation. Experiments under missing-IR settings demonstrate consistent improvements in perceptual quality and downstream detection performance. To our knowledge, this represents the first framework that jointly learns a shared dictionary and performs coefficient-domain inference-fusion to tackle missing-IR fusion. The source code is publicly available at https://github.com/harukiv/DCMIF.