This is the authors' abstract. We don't add key points for this paper.
Thermal imaging holds a pivotal role across diverse applications, yet its efficacy is constrained by the inherent low resolution of widely accessible infrared (IR) cameras. Traditional super-resolution (SR) techniques frequently encounter challenges when applied to thermal images, primarily due to their scarcity of high-frequency details. To mitigate this, guided SR techniques harness information from a high-resolution image, typically captured in the visible spectrum, to facilitate the reconstruction of a highresolution IR image from its low-resolution input. Inspired by SwinFuSR, we propose SwinPaste, an RGB-guided thermal image super-resolution model based on the Swin Transformer. Firstly, we introduce a data mixing strategy during pre-training to enhance data diversity and improve model robustness. Furthermore, we employ multi-scale supervised signals to effectively recover high-frequency details, ensuring superior reconstruction quality. Our proposed method achieves 30.94 PSNR and 0.9201 SSIM at ×8 scale, and 26.33 PSNR and 0.8593 SSIM at ×16 scale on PBVS 2025 dataset, ranking the second place in Track 2 of the PBVS 2025 TISR Challenge.
Answers are grounded in this paper and cite their sources.
No takes yet. Share an insight, caveat, or question.
Zhong et al. (2025) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: