Low-light enhancement technologies are of great significance for visual driver assistance applications and autonomous driving systems. Infrared vision can improve nighttime visibility but also faces challenges of low resolution and lack of color information. This paper presents a unified framework for RGB-guided infrared super-resolution and infrared-visible fusion that achieves high-resolution output under limited computational resources. Our approach employs a U-Net architecture with novel triple-grouped window attention (TGWA) encoding that captures global dependencies through grouped attention while reducing computational overhead, and adaptive multi-dilated convolutional (AMDC) decoding that adaptively selects optimal dilation rates using mixture-of-experts-inspired routing. Experiments on multiple datasets achieve competitive super-resolution and fusion results with minimal computational complexity, while real-world downstream object detection validation confirms robust performance in challenging nighttime scenarios. Quantitatively, the proposed method achieves 28.744 dB/0.872 SSIM on PBVS24 and 31.424 dB/0.882 SSIM on HDRT-Night for 8 & times; infrared super-resolution, reaches competitive fusion quality on both MSRS and HDRT-Night, and attains 69.4% [email protected] in downstream object detection on FLIR_aligned, while requiring only 1.12 M parameters and 85.44 G FLOPs. This work provides new possibilities for seeing clearly in the dark.

Deep Learning for Low-Light Vision: An Efficient Infrared–Visible Fusion Approach

Desantis V;Paracchini MBM;Marcon M.
2026-01-01

Abstract

Low-light enhancement technologies are of great significance for visual driver assistance applications and autonomous driving systems. Infrared vision can improve nighttime visibility but also faces challenges of low resolution and lack of color information. This paper presents a unified framework for RGB-guided infrared super-resolution and infrared-visible fusion that achieves high-resolution output under limited computational resources. Our approach employs a U-Net architecture with novel triple-grouped window attention (TGWA) encoding that captures global dependencies through grouped attention while reducing computational overhead, and adaptive multi-dilated convolutional (AMDC) decoding that adaptively selects optimal dilation rates using mixture-of-experts-inspired routing. Experiments on multiple datasets achieve competitive super-resolution and fusion results with minimal computational complexity, while real-world downstream object detection validation confirms robust performance in challenging nighttime scenarios. Quantitatively, the proposed method achieves 28.744 dB/0.872 SSIM on PBVS24 and 31.424 dB/0.882 SSIM on HDRT-Night for 8 & times; infrared super-resolution, reaches competitive fusion quality on both MSRS and HDRT-Night, and attains 69.4% [email protected] in downstream object detection on FLIR_aligned, while requiring only 1.12 M parameters and 85.44 G FLOPs. This work provides new possibilities for seeing clearly in the dark.
2026
File in questo prodotto:
File Dimensione Formato  
applsci-16-04737-v2.pdf

Accesso riservato

Dimensione 25.14 MB
Formato Adobe PDF
25.14 MB Adobe PDF   Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11311/1330969
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? 0
  • OpenAlex 0
social impact