通过边缘感知机制提升暗光图像细节还原能力
DRWKV: Focusing on Object Edges for Low-Light Image Enhancement
- 引入全局边缘Retinex理论分离光照与边缘结构
- 螺旋扫描注意力捕捉边缘连续性，减少畸变
- 适合需要高保真边缘还原的图像增强场景
暗光图像增强仍面临极端光照退化下保持物体边缘连续性和精细结构的挑战。本文提出新型模型DRWKV（Detailed Receptance Weighted Key Value），融合提出的全局边缘Retinex（GER）理论，实现光照与边缘结构的有效解耦，提升边缘保真度。其次，设计进化式WKV注意力机制，采用螺旋扫描方式更有效捕捉空间边缘连续性并建模不规则结构。第三，提出双边谱对齐模块（Bi-SAB）与定制化MS2-Loss，联合对齐亮度与色度特征，改善视觉自然度并抑制伪影。在五个暗光图像增强基准测试上，DRWKV在PSNR、SSIM和NIQE指标上均达领先表现，同时保持低计算复杂度。此外，该模型显著提升暗光多目标跟踪任务性能，验证其泛化能力。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。