Unveiling Advanced Frequency Disentanglement Paradigm for Low-Light Image Enhancement
This work addresses the problem of enhancing low-light images for computer vision applications, offering a novel paradigm that is incremental but broadly applicable across various models.
The paper tackles low-light image enhancement by proposing an advanced frequency disentanglement paradigm that improves existing methods with minimal computational overhead, achieving up to 7.68dB gains in PSNR on benchmarks.
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.