Impact Factor:5.859
DOI number:10.1109/TCSVT.2022.3194169
Journal:IEEE Transactions on Circuits and Systems for Video Technology
Abstract:Abstract—The learning-based methods for single image super-resolution (SISR) can reconstruct realistic details, but they suffer severe performance degradation for low-light images because of their ignorance of negative effects of illumination, and even produce overexposure for unevenly illuminated images. In this paper, we pioneer an anti-illumination approach toward SISR named Light-guided and Cross-fusion U-Net (LCUN), which can simultaneously improve the texture details and lighting of low-resolution images. In our design, we develop a U-Net for SISR (SRU) to reconstruct super- resolution (SR) images from coarse to fine, effectively suppressing noise and absorbing illuminance information. In particular, the proposed Intensity Estimation Unit (IEU) generates the light intensity map and innovatively guides SRU to adaptively brighten inconsistent illumination. Further, aiming at efficiently utilizing key features and avoiding light interference, an Advanced Fusion Block (AFB) is developed to cross-fuse low-resolution features, reconstructed features and illuminance features in pairs. Moreover, SRU introduces a gate mechanism to dynamically adjust its composition, overcoming the limitations of fixed-scale SR. LCUN is compared with the retrained SISR methods and the combined SISR methods on low-light and uneven-light images. Extensive experiments demonstrate that LCUN advances the state-of-the-arts SISR methods in terms of objective metrics and visual effects, and it can reconstruct relatively clear textures and cope with complex lighting.
Indexed by:Journal paper
Discipline:Engineering
First-Level Discipline:Computer Science and Technology
Document Type:J
Translation or Not:no
Date of Publication:2022-07-20
Included Journals:SCI