Zhang Jiajun, Zhou Yuanbo, Bi Jiang, Xue Yuyang, Deng Wei, He Wenlin, Zhao Tao, Sun Kai, Tong Tong, Gao Qinquan, Zhang Qing
The College of Physics and Information Engineering, Fuzhou University, Fuzhou, 350108, China.
The Beijing Radio and TV Station, Beijing, 100022, China.
Sci Rep. 2024 Apr 25;14(1):9525. doi: 10.1038/s41598-024-60157-9.
The goal of blind image super-resolution (BISR) is to recover the corresponding high-resolution image from a given low-resolution image with unknown degradation. Prior related research has primarily focused effectively on utilizing the kernel as prior knowledge to recover the high-frequency components of image. However, they overlooked the function of structural prior information within the same image, which resulted in unsatisfactory recovery performance for textures with strong self-similarity. To address this issue, we propose a two stage blind super-resolution network that is based on kernel estimation strategy and is capable of integrating structural texture as prior knowledge. In the first stage, we utilize a dynamic kernel estimator to achieve degradation presentation embedding. Then, we propose a triple path attention groups consists of triple path attention blocks and a global feature fusion block to extract structural prior information to assist the recovery of details within images. The quantitative and qualitative results on standard benchmarks with various degradation settings, including Gaussian8 and DIV2KRK, validate that our proposed method outperforms the state-of-the-art methods in terms of fidelity and recovery of clear details. The relevant code is made available on this link as open source.
盲图像超分辨率（BISR）的目标是从给定的具有未知退化的低分辨率图像中恢复相应的高分辨率图像。先前的相关研究主要有效地集中在利用内核作为先验知识来恢复图像的高频分量。然而，他们忽略了同一图像中结构先验信息的作用，这导致对于具有强自相似性的纹理恢复性能不尽人意。为了解决这个问题，我们提出了一种基于内核估计策略的两阶段盲超分辨率网络，该网络能够将结构纹理作为先验知识进行整合。在第一阶段，我们利用动态内核估计器实现退化表示嵌入。然后，我们提出了一个由三路径注意力块和一个全局特征融合块组成的三路径注意力组，以提取结构先验信息来辅助图像细节的恢复。在包括Gaussian8和DIV2KRK在内的各种退化设置的标准基准上的定量和定性结果验证了我们提出的方法在保真度和清晰细节恢复方面优于现有方法。相关代码在该链接作为开源提供。
