Litcius/Paper detail

SCNet: A Self-Calibrating Unsupervised Low-Light Image Enhancement Network

Runze Zhang, Shuanglong Yao, Liang Lü, Xing Wang

2023IEEE Sensors Journal10 citationsDOI

Abstract

Image acquired by camera sensors suffers from low contrast and poor visibility under low-light conditions. Given the importance of enhancing low-light images, this article presents an innovative method known as the self-calibrating neural network (SCNet). This approach involves the extraction of a lighting adjustment feature map (LafMap) from the input image. Matrix operations are then employed on the input image to derive an intermediate image, which is subsequently optimized through self-calibration (SC) to produce the final output image. The SCNet approach has proven effective in experimentation, as indicated by the peak signal-to-noise ratio (PSNR) values, demonstrating a 6.1% increase compared with the baseline on the low-light dataset (LOL dataset). The SCNet can be trained without the necessity for reference images, overcoming the challenge of insufficient enhancement often observed in very low-light images, which is a prominent problem in existing unsupervised low-light enhancement methods.

Topics & Concepts

Artificial intelligenceComputer scienceComputer visionVisibilityFeature extractionCalibrationImage enhancementImage (mathematics)Feature (linguistics)Pattern recognition (psychology)Noise (video)MathematicsOpticsPhysicsStatisticsPhilosophyLinguisticsImage Enhancement TechniquesAdvanced Vision and ImagingAdvanced Image Processing Techniques
SCNet: A Self-Calibrating Unsupervised Low-Light Image Enhancement Network | Litcius