提出首个用于低光增强的专家混合框架，提升跨场景泛化能力。
GM-MoE: Low-Light Enhancement with Gated-Mechanism Mixture-of-Experts
- 采用门控机制动态调节三个专用专家网络权重，适配不同图像域。
- 在5个基准上达到PSNR最优，在4个上达到SSIM最优。
- 适合需要跨场景通用性的低光图像增强任务，如自动驾驶与监控。
低光增强在自动驾驶、三维重建、遥感、监控等领域应用广泛，能显著提升信息利用率。然而，现有方法泛化能力差，多局限于特定任务如图像恢复。为此，我们提出门控机制专家混合（GM-MoE），首个将专家混合网络引入低光图像增强的框架。GM-MoE包含一个动态门控权重调节网络和三个分别专注不同增强任务的子专家网络，并通过自设计的门控机制，根据数据域动态调整各子专家权重。此外，在子专家网络中融合局部与全局特征，以捕捉多尺度信息，提升图像质量。实验表明，GM-MoE在25种对比方法中表现更优，在5个基准上实现最高PSNR，4个基准上达到最高SSIM。
原文摘要 · Abstract (English)
Low-light enhancement has wide applications in autonomous driving, 3D reconstruction, remote sensing, surveillance, and so on, which can significantly improve information utilization. However, most existing methods lack generalization and are limited to specific tasks such as image recovery. To address these issues, we propose Gated-Mechanism Mixture-of-Experts (GM-MoE), the first framework to introduce a mixture-of-experts network for low-light image enhancement. GM-MoE comprises a dynamic gated weight conditioning network and three sub-expert networks, each specializing in a distinct enhancement task. Combining a self-designed gated mechanism that dynamically adjusts the weights of the sub-expert networks for different data domains. Additionally, we integrate local and global feature fusion within sub-expert networks to enhance image quality by capturing multi-scale features. Experimental results demonstrate that the GM-MoE achieves superior generalization with respect to 25 compared approaches, reaching state-of-the-art performance on PSNR on 5 benchmarks and SSIM on 4 benchmarks, respectively.
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。