Text2Thermal：基于文本先验的物理感知热图像合成
Text2Thermal: Physics-Aware Thermal Image Synthesis from Textual Priors
浏览论文内容
中文总结 AI 辅助
针对热数据集稀缺及RGB转热图像的不适定问题，提出Text2Thermal框架，通过热接地文本先验结合适配的Stable Diffusion主干合成热图像，在多数据集上实现最优FID且具备文本级控制能力。
中文摘要 AI 辅助
热红外成像可在黑暗及恶劣天气下提供可靠感知，但热数据集仍较为稀缺，这推动了大量将丰富的RGB图像转换为热图像的研究工作。这种转换本质上是不适定的，因为热外观由表面发射率和物体温度决定，而这两者在可见光光谱中均不可观测，因此单张RGB图像可对应多种有效热输出。我们认为语言是解决这种歧义的自然手段，并提出Text2Thermal——一个基于文本先验的物理感知热图像合成框架。我们不直接从RGB中推断不可观测的辐射度量因子，而是通过编码材料、天气、一天中的时间和热发射状态的热接地描述来明确提供这些因子，并对预训练的Stable Diffusion主干网络进行适配以适配热域。由于辐射度量内容完全由提示词决定，Text2Thermal可在推理时无需注册的RGB图像的情况下合成热图像；若需要空间引导，可选的控制信号可在不干扰提示词指定的辐射度量的情况下赋予场景几何结构。在M3FD、FLIR和FMB数据集上的实验表明，Text2Thermal在热图像合成方法中达到了最先进的FID，同时提供了基于文本的控制能力，这是基于转换的方法无法实现的。
英文摘要
Thermal infrared imaging offers reliable perception in darkness and adverse weather, but thermal datasets remain scarce, motivating extensive work on translating abundant RGB images into thermal. Such translation is fundamentally ill-posed as thermal appearance is governed by surface emissivity and object temperature, neither of which is observable in the visible spectrum, so a single RGB image is consistent with many valid thermal outputs. We argue that language offers a natural means of resolving this ambiguity, and propose **Text2Thermal**, a framework for physics-aware thermal image synthesis from textual priors. Rather than inferring the unobservable radiometric factors from RGB, we supply them explicitly through thermally grounded captions encoding material, weather, time-of-day, and heat-emission state, and adapt a pre-trained Stable Diffusion backbone to the thermal domain. Because the radiometric content is determined entirely by the prompt, Text2Thermal synthesizes thermal imagery without requiring a registered RGB image at inference. Where spatial guidance is desired, an optional control signal imparts scene geometry without disturbing the prompt-specified radiometry. On M3FD and FLIR, Text2Thermal achieves state-of-the-art FID among thermal image synthesis methods, and we additionally report results on the FMB dataset, while offering text-level control that translation-based approaches cannot provide.
发表机构
- School of Engineering, Jawaharlal Nehru University（贾瓦哈拉尔·尼赫鲁大学工程学院）
机构由 AI 辅助整理，请以论文原文为准。
