揭示用于低光图像增强的先进频率解耦范式
Unveiling Advanced Frequency Disentanglement Paradigm for Low-Light Image Enhancement
AI总结：
本文提出一种基于拉普拉斯分解的低频一致性频率解耦范式，以极低计算开销提升多种低光图像增强模型性能，在多个基准上实现最高7.68dB PSNR增益。
摘要：
以往的低光图像增强（LLIE）方法虽然采用频率分解技术来应对低频（如光照恢复）和高频（如噪声抑制）相互交织的挑战，但主要侧重于开发专用且复杂的网络以取得更好的性能。与之不同，我们揭示了一种先进的解耦范式，仅需极小的计算开销即可持续提升最先进方法的表现。借助图像拉普拉斯分解方案，我们提出了一种新颖的低频一致性方法，从而促进更优的频率解耦优化。我们的方法能够无缝集成到CNN、Transformer、基于流的模型和扩散模型等多种模型中，展现出显著的适应性。在五个常用基准上展示了显著的改进，六个最先进模型在PSNR上最高获得了7.68dB的提升。令人印象深刻的是，我们的方法仅增加88K额外参数即可保持高效，在低光图像增强这一具有挑战性的领域中树立了新标准。
英文摘要：
Previous low-light image enhancement (LLIE) approaches, while employing frequency decomposition techniques to address the intertwined challenges of low frequency (e.g., illumination recovery) and high frequency (e.g., noise reduction), primarily focused on the development of dedicated and complex networks to achieve improved performance. In contrast, we reveal that an advanced disentanglement paradigm is sufficient to consistently enhance state-of-the-art methods with minimal computational overhead. Leveraging the image Laplace decomposition scheme, we propose a novel low-frequency consistency method, facilitating improved frequency disentanglement optimization. Our method, seamlessly integrating with various models such as CNNs, Transformers, and flow-based and diffusion models, demonstrates remarkable adaptability. Noteworthy improvements are showcased across five popular benchmarks, with up to 7.68dB gains on PSNR achieved for six state-of-the-art models. Impressively, our approach maintains efficiency with only 88K extra parameters, setting a new standard in the challenging realm of low-light image enhancement.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
