3M-TI：基于免标定多相机跨模态扩散的高质量移动热成像
3M-TI: High-Quality Mobile Thermal Imaging via Calibration-free Multi-Camera Cross-Modal Diffusion
把扩散 UNet 中的自注意力层替换为跨模态自注意力（CSM），在去噪过程中自适应对齐热成像与 RGB 特征，从而绕开相机标定；这一「免标定跨模态特征对齐 + 生成先验」的思路可直接迁移到其他多传感器图像复原任务（如低光 RGB-NIR 增强、深度引导超分）。
原文依据 integrates a cross-modal self-attention module (CSM) into the diffusion UNet, replacing the original self-attention layers
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论面向移动平台的热传感器小型化从根本上限制了其空间分辨率与纹理保真度，导致图像模糊且信息量不足。现有的热成像超分辨率（SR）方法可分为单图像方法与 RGB 引导方法两类：前者难以从有限信息中恢复精细结构，后者依赖精确且繁琐的跨相机标定，从而阻碍了实际部署与鲁棒性。为此，本文提出 3M-TI，一种面向移动热成像的免标定多相机跨模态扩散框架。3M-TI 的核心是在扩散 UNet 中引入跨模态自注意力模块（CSM），替换原有的自注意力层，从而在整个去噪过程中自适应地对齐热成像与 RGB 特征，且无需显式的相机标定。该设计使扩散网络能够利用其生成先验来提升超分热图像的空间分辨率、结构保真度与纹理细节。在真实移动热相机与公开基准上的大量评估验证了本方法的优越性能，在视觉质量与定量指标上均取得最优结果。更重要的是，经 3M-TI 增强的热图像在目标检测与分割等关键下游任务上带来显著增益，凸显了其对构建鲁棒移动热感知系统的实用价值。
英文原文摘要 1480 字符
The miniaturization of thermal sensors for mobile platforms inherently limits their spatial resolution and textural fidelity, leading to blurry and less informative images. Existing thermal super-resolution (SR) methods can be grouped into single-image and RGB-guided approaches: the former struggles to recover fine structures from limited information, while the latter relies on accurate and laborious cross-camera calibration, which hinders practical deployment and robustness. Here, we propose 3M-TI, a calibration-free Multi-camera cross-Modality diffusion framework for Mobile Thermal Imaging. At its core, 3M-TI integrates a cross-modal self-attention module (CSM) into the diffusion UNet, replacing the original self-attention layers to adaptively align thermal and RGB features throughout the denoising process, without requiring explicit camera calibration. This design enables the diffusion network to leverage its generative prior to enhance spatial resolution, structural fidelity, and texture detail in the super-resolved thermal images. Extensive evaluations on real-world mobile thermal cameras and public benchmarks validate our superior performance, achieving state-of-the-art results in both visual quality and quantitative metrics. More importantly, the thermal images enhanced by 3M-TI lead to substantial gains in critical downstream tasks like object detection and segmentation, underscoring its practical value for robust mobile thermal perception systems.