让红外图像生成更真实，通过热物理知识控制光照与天气变化
TherA: Thermal-Aware Visual-Language Prompting for Controllable RGB-to-Thermal Infrared Translation
- 用视觉语言模型捕捉热特性，生成符合物理规律的红外图
- 在零样本条件下性能提升最高达33%，支持时间/天气/物体状态调控
- 适合需要高保真红外数据的自动驾驶与安防场景
尽管热成像具有天然优势，但大规模数据采集与标注仍是基于热成像感知的主要瓶颈。一个实用替代方案是通过图像转换合成伪红外数据；然而，大多数RGB到红外方法严重依赖可见光先验，忽略热物理规律，导致热分布不自然。本文提出TherA，一种可控的RGB到红外图像转换框架，能在场景和物体层面生成多样且热学合理的图像。TherA结合TherA-VLM与基于潜在扩散的翻译器：给定单张RGB图像和用户提示条件对，TherA-VLM生成编码了场景、物体、材料及热辐射上下文的热感知嵌入。将扩散模型以此嵌入为条件，实现逼真的红外合成，并可精细控制昼夜、天气和物体状态。相比其他基线方法，TherA达到最优翻译性能，在所有指标上平均零样本性能提升达33%。
原文摘要 · Abstract (English)
Despite the inherent advantages of thermal infrared(TIR) imaging, large-scale data collection and annotation remain a major bottleneck for TIR-based perception. A practical alternative is to synthesize pseudo TIR data via image translation; however, most RGB-to-TIR approaches heavily rely on RGB-centric priors that overlook thermal physics, yielding implausible heat distributions. In this paper, we introduce TherA, a controllable RGB-to-TIR translation framework that produces diverse and thermally plausible images at both scene and object level. TherA couples TherA-VLM with a latent-diffusion-based translator. Given a single RGB image and a user-prompted condition pair, TherA-VLM yields a thermal-aware embedding that encodes scene, object, material, and heat-emission context reflecting the input scene-condition pair. Conditioning the diffusion model on this embedding enables realistic TIR synthesis and fine-grained control across time of day, weather, and object state. Compared to other baselines, TherA achieves state-of-the-art translation performance, demonstrating improved zero-shot translation performance up to 33% increase averaged across all metrics.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。