RHVI-FDD: A Hierarchical Decoupling Framework for Low-Light Image Enhancement

TL;DR

This paper introduces RHVI-FDD, a hierarchical framework that effectively decouples and enhances low-light images by separating luminance, chrominance, noise, and details using a novel transform and frequency-domain modules.

Contribution

The proposed framework combines a macro-level RHVI transform with micro-level frequency-domain decoupling modules, enabling simultaneous correction of color, noise suppression, and detail preservation.

Findings

Outperforms state-of-the-art methods on multiple low-light datasets.

Achieves better objective metrics and visual quality.

Effectively separates noise, details, and color distortions.

Abstract

Low-light images often suffer from severe noise, detail loss, and color distortion, which hinder downstream multimedia analysis and retrieval tasks. The degradation in low-light images is complex: luminance and chrominance are coupled, while within the chrominance, noise and details are deeply entangled, preventing existing methods from simultaneously correcting color distortion, suppressing noise, and preserving fine details. To tackle the above challenges, we propose a novel hierarchical decoupling framework (RHVI-FDD). At the macro level, we introduce the RHVI transform, which mitigates the estimation bias caused by input noise and enables robust luminance-chrominance decoupling. At the micro level, we design a Frequency-Domain Decoupling (FDD) module with three branches for further feature separation. Using the Discrete Cosine Transform, we decompose chrominance features into low, mid, and high-frequency bands that predominantly represent global tone, local details, and noise components, which are then processed by tailored expert networks in a divide-and-conquer manner and fused via an adaptive gating module for content-aware fusion. Extensive experiments on multiple low-light datasets demonstrate that our method consistently outperforms existing state-of-the-art approaches in both objective metrics and subjective visual quality.