AI RESEARCH
Lightweight Low-Light Image Enhancement via Distribution-Normalizing Preprocessing and Depthwise U-Net
arXiv CS.AI
•
ArXi:2604.11071v1 Announce Type: cross We present a lightweight two-stage framework for low-light image enhancement (LLIE) that achieves competitive perceptual quality with significantly fewer parameters than existing methods. Our approach combines frozen algorithm-based preprocessing with a compact U-Net built entirely from depthwise-separable convolutions. The preprocessing normalizes the input distribution by providing complementary brightness-corrected views, enabling the trainable network to focus on residual color correction.