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

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Bai, Xuecheng, Wang, Yuxiang, Hu, Boyu, Jie, Qinyuan, Xu, Chuanzhi, Li, Kechen, Xiao, Hongru, Chung, Vera
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866918235179319296
author Bai, Xuecheng
Wang, Yuxiang
Hu, Boyu
Jie, Qinyuan
Xu, Chuanzhi
Li, Kechen
Xiao, Hongru
Chung, Vera
author_facet Bai, Xuecheng
Wang, Yuxiang
Hu, Boyu
Jie, Qinyuan
Xu, Chuanzhi
Li, Kechen
Xiao, Hongru
Chung, Vera
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2507_18594
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DRWKV: Focusing on Object Edges for Low-Light Image Enhancement
Bai, Xuecheng
Wang, Yuxiang
Hu, Boyu
Jie, Qinyuan
Xu, Chuanzhi
Li, Kechen
Xiao, Hongru
Chung, Vera
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
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.
title DRWKV: Focusing on Object Edges for Low-Light Image Enhancement
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2507.18594