Noise-Aware Texture-Preserving Low-Light Enhancement

TL;DR

This paper introduces NATLE, a low-light image enhancement method that effectively balances noise removal and texture preservation using a noise-aware retinex model, demonstrated through extensive experiments.

Contribution

The paper presents a novel noise-aware retinex-based approach for low-light enhancement that maintains natural textures while reducing noise, with a low-complexity implementation.

Findings

Superior performance on standard datasets

Effective noise and texture preservation

Low computational complexity

Abstract

A simple and effective low-light image enhancement method based on a noise-aware texture-preserving retinex model is proposed in this work. The new method, called NATLE, attempts to strike a balance between noise removal and natural texture preservation through a low-complexity solution. Its cost function includes an estimated piece-wise smooth illumination map and a noise-free texture-preserving reflectance map. Afterwards, illumination is adjusted to form the enhanced image together with the reflectance map. Extensive experiments are conducted on common low-light image enhancement datasets to demonstrate the superior performance of NATLE.