DRWKV: Focusing on Object Edges for Low-Light Image Enhancement

TL;DR

This paper introduces DRWKV, a novel low-light image enhancement model that effectively preserves object edges and details by integrating edge-aware theories, attention mechanisms, and feature alignment techniques, achieving superior results and generalization.

Contribution

The paper presents DRWKV, a new model combining Global Edge Retinex theory, Evolving WKV Attention, and Bilateral Spectrum Aligner for improved low-light image enhancement.

Findings

Achieves state-of-the-art PSNR, SSIM, and NIQE on five benchmarks.

Enhances downstream low-light multi-object tracking performance.

Maintains low computational complexity.

Abstract

Low-light image enhancement remains a challenging task, particularly in preserving object edge continuity and fine structural details under extreme illumination degradation. In this paper, we propose a novel model, DRWKV (Detailed Receptance Weighted Key Value), which integrates our proposed Global Edge Retinex (GER) theory, enabling effective decoupling of illumination and edge structures for enhanced edge fidelity. Secondly, we introduce Evolving WKV Attention, a spiral-scanning mechanism that captures spatial edge continuity and models irregular structures more effectively. Thirdly, we design the Bilateral Spectrum Aligner (Bi-SAB) and a tailored MS2-Loss to jointly align luminance and chrominance features, improving visual naturalness and mitigating artifacts. Extensive experiments on five LLIE benchmarks demonstrate that DRWKV achieves leading performance in PSNR, SSIM, and NIQE while maintaining low computational complexity. Furthermore, DRWKV enhances downstream performance in low-light multi-object tracking tasks, validating its generalization capabilities.