Research
Lightweight Low-Light Image Enhancement via Distribution-Normalizing Preprocessing and Depthwise U-Net
arXiv:2604.11071v1 Announce Type: cross Abstract: We present a lightweight two-stage framework for low-light image enhancement (LLIE) that achieves competitive perceptual quality with significantly fe
arXiv:2604.11071v1 Announce Type: cross Abstract: 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. Our method achieved 4th place in the CVPR 2026 NTIRE Efficient Low-Light Image Enhancement Challenge. We further provide extended benchmarks and ablations to demonstrate the general effectiveness of our methods.
Related
- Multinex: Lightweight Low-light Image Enhancement via Multi-prior Retinex
- Implantable Adaptive Cells: A Novel Enhancement for Pre-Trained U-Nets in Medical Image Segmentation
- UDAPose: Unsupervised Domain Adaptation for Low-Light Human Pose Estimation
- PSIRNet: Deep Learning-based Free-breathing Rapid Acquisition Late Enhancement Imaging
Source: arXiv cs.AI | 2026-04-14