ThermalGen：基於風格解耦流模型的RGB至熱成像圖像轉換生成器
ThermalGen: Style-Disentangled Flow-Based Generative Models for RGB-to-Thermal Image Translation
September 29, 2025
作者: Jiuhong Xiao, Roshan Nayak, Ning Zhang, Daniel Tortei, Giuseppe Loianno
cs.AI
摘要
配對的RGB-熱成像數據對於視覺-熱成像傳感器融合及跨模態任務至關重要，這些任務包括多模態圖像對齊與檢索等重要應用。然而，同步且校準的RGB-熱成像圖像對的稀缺性，成爲這些領域進展的主要障礙。爲克服這一挑戰，RGB至熱成像（RGB-T）圖像轉換技術應運而生，它能夠從豐富的RGB數據集中合成熱成像圖像，用於訓練目的。在本研究中，我們提出了ThermalGen，一種基於自適應流的生成模型，用於RGB-T圖像轉換，該模型融合了RGB圖像條件架構和風格解耦機制。爲支持大規模訓練，我們整理了八個公開的衛星-航空、航空及地面RGB-T配對數據集，並引入了三個新的大規模衛星-航空RGB-T數據集——DJI-day、Bosonplus-day和Bosonplus-night，這些數據集捕捉了不同時間、傳感器類型和地理區域的圖像。在多個RGB-T基準上的廣泛評估表明，ThermalGen在轉換性能上與現有的基於GAN和擴散的方法相當或更優。據我們所知，ThermalGen是首個能夠合成反映顯著視角變化、傳感器特性和環境條件變化的熱成像圖像的RGB-T圖像轉換模型。項目頁面：http://xjh19971.github.io/ThermalGen
English
Paired RGB-thermal data is crucial for visual-thermal sensor fusion and
cross-modality tasks, including important applications such as multi-modal
image alignment and retrieval. However, the scarcity of synchronized and
calibrated RGB-thermal image pairs presents a major obstacle to progress in
these areas. To overcome this challenge, RGB-to-Thermal (RGB-T) image
translation has emerged as a promising solution, enabling the synthesis of
thermal images from abundant RGB datasets for training purposes. In this study,
we propose ThermalGen, an adaptive flow-based generative model for RGB-T image
translation, incorporating an RGB image conditioning architecture and a
style-disentangled mechanism. To support large-scale training, we curated eight
public satellite-aerial, aerial, and ground RGB-T paired datasets, and
introduced three new large-scale satellite-aerial RGB-T datasets--DJI-day,
Bosonplus-day, and Bosonplus-night--captured across diverse times, sensor
types, and geographic regions. Extensive evaluations across multiple RGB-T
benchmarks demonstrate that ThermalGen achieves comparable or superior
translation performance compared to existing GAN-based and diffusion-based
methods. To our knowledge, ThermalGen is the first RGB-T image translation
model capable of synthesizing thermal images that reflect significant
variations in viewpoints, sensor characteristics, and environmental conditions.
Project page: http://xjh19971.github.io/ThermalGen