TherA: Thermal-Aware Visual-Language Prompting for Controllable RGB-to-Thermal Infrared Translation

TL;DR

TherA is a novel controllable RGB-to-thermal infrared translation framework that synthesizes thermally plausible images with fine-grained control, overcoming limitations of RGB-centric priors and enhancing zero-shot translation performance.

Contribution

TherA introduces a thermal-aware embedding and a diffusion-based translator for realistic, controllable TIR image synthesis from RGB images, incorporating scene and object heat context.

Findings

Achieves state-of-the-art translation performance

Improves zero-shot translation by up to 33%

Enables fine-grained control over synthesis parameters

Abstract

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.