超越严格配对：面向高性能红外与可见光图像融合的任意配对训练
Beyond Strict Pairing: Arbitrarily Paired Training for High-Performance Infrared and Visible Image Fusion
把红外与可见光图像融合的训练从严格配对中解放出来，用非配对/任意配对数据即可训练，并给出 CNN/Transformer/GAN 三个轻量基线；做多模态融合或跨模态配准数据稀缺时，可直接复用其任意配对训练目标与配套损失函数。
原文依据 this work challenges the necessity of Strictly Paired Training Paradigm (SPTP) by systematically investigating UnPaired and Arbitrarily Paired Training Paradigms
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与可见光图像融合（IVIF）旨在合成两种源模态的互补信息，同时保留自然纹理与显著热特征。现有方案主要依赖大量严格对齐的图像对进行训练。然而，由于对齐过程成本高昂且耗费人力，获取此类数据往往不切实际。此外，训练中维持严格配对设定限制了跨模态关系的数量，从而限制了泛化性能。为此，本工作通过系统研究非配对训练范式（UPTP）与任意配对训练范式（APTP）以实现高性能 IVIF，对严格配对训练范式（SPTP）的必要性提出挑战。我们建立了 APTP 的理论目标，反映了 UPTP 与 SPTP 之间的互补性。更重要的是，我们开发了一个实用框架，即使在训练数据严重受限且未对齐的情况下，也能显著丰富跨模态关系。为验证上述主张，我们设计了三个端到端轻量基线以及一组创新损失函数，覆盖三种经典框架（CNN、Transformer、GAN）。大量实验表明，所提出的 APTP 与 UPTP 是可行的，能够在严重受限且内容不一致的红外与可见光数据集上训练模型，并取得与 SPTP 下大 100 倍数据集相当的性能。这一发现从根本上缓解了数据采集的成本与难度，同时从数据角度增强了模型鲁棒性，为 IVIF 研究提供了可行方案。
英文原文摘要 1701 字符
Infrared and visible image fusion (IVIF) aims to synthesise complementary information from the two source modalities while preserving natural textures and salient thermal signatures simultaneously. Existing solutions predominantly rely on extensive sets of rigidly aligned image pairs for training. However, acquiring such data is often impractical due to the costly and labour-intensive alignment process. Besides, maintaining a rigid pairing setting during training restricts the volume of cross-modal relationships, thereby limiting the generalisation performance. To this end, this work challenges the necessity of Strictly Paired Training Paradigm (SPTP) by systematically investigating UnPaired and Arbitrarily Paired Training Paradigms (UPTP and APTP) for high-performance IVIF. We establish a theoretical objective of APTP, reflecting the complementary nature between UPTP and SPTP. More importantly, we develop a practical framework capable of significantly enriching cross-modal relationships even with severely limited and unaligned training data. To validate our propositions, three end-to-end lightweight baselines, alongside a set of innovative loss functions, are designed to cover three classic frameworks (CNN, Transformer, GAN). Comprehensive experiments demonstrate that the proposed APTP and UPTP are feasible and capable of training models on a severely limited and content-inconsistent infrared and visible dataset, achieving performance comparable to that of a dataset 100xlarger in SPTP. This finding fundamentally alleviates the cost and difficulty of data collection while enhancing model robustness from the data perspective, delivering a feasible solution for IVIF studies.