Metraipolis › archive › dc_5e2868e4e7ab

TIRMamba: A Thermal-Prior-Modulated State-Space Network for Sub-Million-Parameter Infrared Image Super-Resolution — arXiv:2610.05182

Source
arXiv
Original
https://arxiv.org/abs/2610.05182
License (as archived)
CC0-1.0
Archived
2026-10-06T05:32:16.963Z
SHA-256 of the archived text
807f428fa836f1cb2e65b5fd4c8657d590983a9cd3503a7597172d6e8203025e
Stable URL of this page
https://metraipolis.com/documento/dc_5e2868e4e7ab

How to cite

TIRMamba: A Thermal-Prior-Modulated State-Space Network for Sub-Million-Parameter Infrared Image Super-Resolution — arXiv:2610.05182 — arXiv, https://arxiv.org/abs/2610.05182 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5e2868e4e7ab (Metraipolis archive dc_5e2868e4e7ab, sha256 807f428fa836f1cb2e65b5fd4c8657d590983a9cd3503a7597172d6e8203025e)
BibTeX
@misc{dc5e2868e4e7ab,
  title = {TIRMamba: A Thermal-Prior-Modulated State-Space Network for Sub-Million-Parameter Infrared Image Super-Resolution — arXiv:2610.05182},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.05182},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5e2868e4e7ab; sha256 807f428fa836f1cb2e65b5fd4c8657d590983a9cd3503a7597172d6e8203025e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.05182. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Infrared image super-resolution is currently led by Mamba-based networks with 26 to 37 million parameters, which are difficult to deploy on the airborne and handheld platforms where thermal imaging is most needed. This paper presents TIRMamba, a network with 896K to 910K parameters for single-channel thermal imagery. A Thermal Prior Highway computes gradient, local-contrast and spectral cues once at the input and, through one adapter per residual group, modulates a weight-tied bidirectional state-space trunk and gates its dual-scale detail branch; a tri-path reconstruction adds the learned residual to a bicubic radiometric baseline. Because the standard benchmark provides only 265 infrared training images and evaluates fusion products on full images, we train with a replay strategy: grayscale DIV2K pre-training followed by fine-tuning on 64-pixel patches drawn with equal probability from the infrared and natural corpora. At scale factor 4, TIRMamba matches the strongest protocol-trained methods on both official test sets with 29 to 40 times fewer parameters and 2.8 to 9.4 times lower latency; at scale factor 2 it gives the highest SSIM on both. A variant with prior-conditioned selectivity, TIRMamba-Rad, corrects a 3 dB raw-thermal failure of an intermediate size-invariant design and gives the best results at scale factor 4 on raw-thermal, unmanned-aerial-vehicle and independent-sensor test sets. Code and trained models will be released at this https URL upon acceptance.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Image and Video Processing (eess.IV) ; Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.05182 — 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 2026-10-06T05:27:05.995Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).