Preprint
Oct 2026
PRIN: A Perceptual-Structural Retinex-Inspired Network for Low-Light Image Enhancement
A Perceptual-Structural Retinex-Inspired Network (PRIN), which integrates Retinex priors with restoration-role-aware enhancement and obtains the highest peak signal-to-noise ratio (PSNR) and the second-lowest LPIPS on LOL-v2-Real.
Qi-Yi Xie, Wei-Chen Ng, Zi-Yao Li et al.
· 0 citations