DPEC: Dual-Path Error Compensation Method for Enhanced Low-Light Image Clarity

TL;DR

The paper introduces DPEC, a novel deep learning method that enhances low-light images by effectively preserving details and reducing noise, outperforming existing techniques through a dual-path approach and specialized loss functions.

Contribution

It proposes the Dual-Path Error Compensation (DPEC) method with pixel-level error estimation, an independent denoising mechanism, and the HIS-Retinex loss for improved low-light image enhancement.

Findings

DPEC achieves superior quantitative performance over state-of-the-art methods.

DPEC effectively preserves local textures and reduces noise amplification.

The method demonstrates strong qualitative improvements in low-light image clarity.

Abstract

For the task of low-light image enhancement, deep learning-based algorithms have demonstrated superiority and effectiveness compared to traditional methods. However, these methods, primarily based on Retinex theory, tend to overlook the noise and color distortions in input images, leading to significant noise amplification and local color distortions in enhanced results. To address these issues, we propose the Dual-Path Error Compensation (DPEC) method, designed to improve image quality under low-light conditions by preserving local texture details while restoring global image brightness without amplifying noise. DPEC incorporates precise pixel-level error estimation to capture subtle differences and an independent denoising mechanism to prevent noise amplification. We introduce the HIS-Retinex loss to guide DPEC's training, ensuring the brightness distribution of enhanced images closely aligns with real-world conditions. To balance computational speed and resource efficiency while training DPEC for a comprehensive understanding of the global context, we integrated the VMamba architecture into its backbone. Comprehensive quantitative and qualitative experimental results demonstrate that our algorithm significantly outperforms state-of-the-art methods in low-light image enhancement. The code is publicly available online at https://github.com/wangshuang233/DPEC.