mlsanityData to 7 Oct 2026

Lightweight Low-Light Image Enhancement via Distribution-Normalizing Preprocessing and Depthwise U-Net

arXiv 2604.11071 ↗First posted 13 Apr 2026cs.CV cs.AI cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

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 3rd 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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 17 of its 23 references that are in the map. First posted on arXiv 13 Apr 2026.

Builds on

17 of 23 references.

References · 17

  1. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  2. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,827
  3. 2021MUSIQ: Multi-scale Image Quality Transformercited by 1,058
  4. 2020Image Quality Assessment: Unifying Structure and Texture Similaritycited by 792
  5. 2018Deep Retinex Decomposition for Low-Light Enhancementcited by 720
  6. 2022Simple Baselines for Image Restorationcited by 701
  7. 2020Zero-Reference Deep Curve Estimation for Low-Light Image Enhancementcited by 541
  8. 2019Kindling the Darkness: A Practical Low-light Image Enhancercited by 355
  9. 2023Blind Image Quality Assessment via Vision-Language Correspondence: A Multitask Learning Perspectivecited by 276
  10. 2023Retinexformer: One-stage Retinex-based Transformer for Low-light Image Enhancementcited by 228
  11. 2022Ultra-High-Definition Low-Light Image Enhancement: A Benchmark and Transformer-Based Methodcited by 174
  12. 2023Diff-Retinex: Rethinking Low-light Image Enhancement with A Generative Diffusion Modelcited by 118
5 more
  1. 2022You Only Need 90K Parameters to Adapt Light: A Light Weight Transformer for Image Enhancement and Exposure Correctioncited by 81
  2. 2021Low-light Image Enhancement via Breaking Down the Darknesscited by 65
  3. 2024Retinexmamba: Retinex-based Mamba for Low-light Image Enhancementcited by 59
  4. 2024LYT-NET: Lightweight YUV Transformer-based Network for Low-light Image Enhancementcited by 22
  5. 2024A Lightweight Low-Light Image Enhancement Network via Channel Prior and Gamma Correctioncited by 6

Built on by

Not cited yet.