Metraipolis › archive › dc_87b592db37d5

Text2Thermal: Physics-Aware Thermal Image Synthesis from Textual Priors — arXiv:2609.03585

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.03585
License (as archived)
CC0-1.0
Archived
2026-10-17T02:56:21.271Z
SHA-256 of the archived text
c23f92ec9fcaaa176a2f6082f40ae6984e1166b0c3bb1bf6fdc23760f2786952
Stable URL of this page
https://metraipolis.com/documento/dc_87b592db37d5

How to cite

Text2Thermal: Physics-Aware Thermal Image Synthesis from Textual Priors — arXiv:2609.03585 — arXiv (en), https://arxiv.org/abs/2609.03585 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_87b592db37d5 (Metraipolis archive dc_87b592db37d5, sha256 c23f92ec9fcaaa176a2f6082f40ae6984e1166b0c3bb1bf6fdc23760f2786952)
BibTeX
@misc{dc87b592db37d5,
  title = {Text2Thermal: Physics-Aware Thermal Image Synthesis from Textual Priors — arXiv:2609.03585},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.03585},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_87b592db37d5; sha256 c23f92ec9fcaaa176a2f6082f40ae6984e1166b0c3bb1bf6fdc23760f2786952},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.03585. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-04 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.03585 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T02:27:18.973Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-04?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).