用蝴蝶与萤火虫算法自动优化低光图像增强参数，效果优于传统方法。
BFORE: Butterfly-Firefly Optimized Retinex Enhancement for Low-Light Image Quality Improvement
- 结合蝴蝶与萤火虫算法，自动搜索最佳增强参数。
- 在合成与真实图像上GNS分别达0.971和0.887，领先同行8.6%~14.7%。
- 适合对图像自然度要求高且可接受离线处理的场景。
低光图像普遍存在可见度差、噪声大和色彩失真问题。现有基于Retinex的方法依赖人工调参，难以跨光照条件泛化。本文提出BFORE（蝴蝶-萤火虫优化的Retinex增强），通过两阶段优化自动为每张图像寻找最优参数：第一阶段使用蝴蝶优化算法（BOA）搜索多尺度Retinex带颜色恢复（MSRCR）参数；第二阶段用萤火虫算法（FA）微调伽马校正、去噪和色彩参数。两阶段均以无参考的高斯自然度评分（GNS）为目标函数。标准指标（PSNR、SSIM、NIQE）仅在优化后计算，避免数据泄露。在30对合成图像上，BFORE取得GNS=0.971，优于次优方法MSRCR（0.894）8.6%；在LOL数据集115张真实图像上，GNS=0.887，优于MSRCR（0.808）9.8%。与三类深度学习基线（Zero-DCE、SCI、IAT）在相同条件下对比，BFORE超越最佳模型14.7%。消融实验表明混合优化策略显著优于单一算法，且在不同计算预算下（128、300次评估）均显著优于随机采样（p<0.021）。所有改进均具统计显著性（p<0.0001，Wilcoxon检验）。单图处理时间3-6分钟，适用于离线应用。
原文摘要 · Abstract (English)
Low-light images suffer from poor visibility, noise, and color distortion. Existing Retinex-based enhancement methods rely on manually tuned parameters that do not generalize across different lighting conditions. This paper proposes BFORE (Butterfly-Firefly Optimized Retinex Enhancement), a framework that automatically finds the best enhancement parameters for each image. BFORE works in two phases: (1) a Butterfly Optimization Algorithm (BOA) searches for optimal Multi-Scale Retinex with Color Restoration (MSRCR) parameters, then (2) a Firefly Algorithm (FA) fine-tunes gamma correction, denoising, and color parameters. Both phases maximize a Gaussian Naturalness Score (GNS), a no-reference metric that measures how natural the enhanced image looks. Standard quality metrics (PSNR, SSIM, NIQE) are computed only after optimization, ensuring zero data leakage. On 30 synthetic image pairs, BFORE achieves GNS = 0.971, outperforming the next-best method MSRCR (0.894) by 8.6%. On 115 real images from the LOL dataset, BFORE achieves GNS = 0.887, outperforming MSRCR (0.808) by 9.8%. A controlled comparison with three deep learning baselines (Zero-DCE, SCI, IAT) trained under identical conditions shows BFORE surpasses the best DL method by 14.7% in GNS. An ablation study confirms that the hybrid BOA+FA strategy significantly outperforms each optimizer in isolation, and a scalability analysis at three evaluation budgets shows that the structured optimizer significantly outperforms uniform random sampling once compute is available (p = 0.009 at 128 evaluations, p = 0.021 at 300 evaluations). All improvements are statistically significant (p < 0.0001, Wilcoxon signed-rank test). Processing time is 3-6 minutes per image on CPU, suitable for offline applications.
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。