Images captured under low-light conditions usually co-exist with low light and blur degradation. Most existing cascade and joint enhancement methods may provide undesirable results, suffering from severe artifacts, deteriorating blur, and unclear details. In this paper, we propose a novel network with structural priors, including high-frequency and edge, to enable effective image representation learning for joint low-light enhancement and deblurring. Specifically, we employ a Transformer backbone to explore the global clues of the image. To compensate for the inadequate local detail optimization, we propose a multi-patch perception pyramid block that models the correlation between different size patches and ambiguity, and identifies non-uniform deblurring spatial features, facilitating the reconstruction of potential high-frequency and edge information. Furthermore, a prior-guided reconstruction block based on the parallel attention mechanism is present to adaptively correct global image with statistical features, which helps guide the model to refine sharp texture and structure. Extensive experiments performed on simulated and real-world datasets demonstrate the efficacy of our proposed method in restoring low-light blurry and low-light images with increased visual perception compared to state-of-the-art methods.

中文翻译：

---

通过结构先验指导进行联合低光增强和去模糊

在低光条件下拍摄的图像通常与低光和模糊退化共存。大多数现有的级联和联合增强方法可能会提供不理想的结果，遭受严重的伪影、恶化的模糊和不清楚的细节。在本文中，我们提出了一种具有结构先验（包括高频和边缘）的新型网络，以实现有效的图像表示学习，以进行联合低光增强和去模糊。具体来说，我们采用 Transformer 主干来探索图像的全局线索。为了弥补局部细节优化的不足，我们提出了一种多块感知金字塔块，它可以对不同大小块和模糊度之间的相关性进行建模，并识别非均匀去模糊空间特征，从而促进潜在高频和边缘信息的重建。此外，提出了基于并行注意机制的先验引导重建块，以利用统计特征自适应校正全局图像，这有助于指导模型细化清晰的纹理和结构。在模拟和真实数据集上进行的大量实验证明了我们提出的方法在恢复低光模糊和低光图像方面的有效性，与最先进的方法相比，视觉感知增强。