Thermal image super-resolution : trends and challenges
Rivadeneira, Rafael E. (Escuela Superior Politécnica del Litoral (Ecuador))
Sappa, Angel (Centre de Visió per Computador)
Hammoud, Riad

Date:	2025
Abstract:	Thermal Image Super-Resolution has become pivotal for security, autonomous driving, industrial inspection, and surveillance. This work consolidates six editions of the TISR challenge held within the Perception Beyond the Visible Spectrum workshop at CVPR from 2020 to 2025, detailing the evolution of tasks, datasets, evaluation protocols, and participation. The analysis traces a methodological shift from convolutional neural networks to transformer-based and hybrid architectures that better capture long-range dependencies, besides the emergence of cross-spectral guidance that leverages visible imagery to enhance thermal detail at large scale factors. Quantitative trends in PSNR and SSIM across editions show consistent improvement in results. Remaining challenges include robust cross-spectral alignment, computational efficiency for resource-constrained deployment, broader dataset diversity across conditions, and resilience to noise and environmental variation. The synthesis provides a unified reference for benchmarking progress and outlines actionable directions for future advances in thermal image reconstruction.
Rights:	Aquest document està subjecte a una llicència d'ús Creative Commons. Es permet la reproducció total o parcial, la distribució, i la comunicació pública de l'obra, sempre que no sigui amb finalitats comercials, i sempre que es reconegui l'autoria de l'obra original. No es permet la creació d'obres derivades.
Language:	Anglès
Document:	Article ; recerca ; Versió publicada
Subject:	Thermal imaging ; Super-resolution ; Cross-spectral guidance ; Deep learning ; Transformers ; Benchmark datasets
Published in:	ELCVIA, Vol. 24, Num. 2 (2025) , p. 355-372 (Regular Issue) , ISSN 1577-5097

Adreça original: https://elcvia.cvc.uab.cat/article/view/2374
DOI: 10.5565/rev/elcvia.2374

18 p, 4.5 MB

The record appears in these collections:
Articles > Published articles > ELCVIA
Articles > Research articles