Text2Thermal: Physics-Aware Thermal Image Synthesis from Textual Priors

Text2Thermal is a new framework that generates physics‑aware thermal images directly from textual descriptions. By providing thermally grounded captions that encode material properties, weather, time of day, and heat‑emission state, the method bypasses the need to infer unobservable radiometric factors from RGB images. It adapts a Stable Diffusion backbone to the thermal domain, optionally using a control signal for scene geometry, and achieves state‑of‑the‑art FID scores on M3FD, FLIR, and FMB datasets.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

• diffusion
• benchmarks