School of Information, Xiamen University, Xiamen 361005, China.
School of Science, Jimei University, Xiamen 361021, China.
Sensors (Basel). 2023 Jun 5;23(11):5338. doi: 10.3390/s23115338.
Image super-resolution (SR) usually synthesizes degraded low-resolution images with a predefined degradation model for training. Existing SR methods inevitably perform poorly when the true degradation does not follow the predefined degradation, especially in the case of the real world. To tackle this robustness issue, we propose a cascaded degradation-aware blind super-resolution network (CDASRN), which not only eliminates the influence of noise on blur kernel estimation but also can estimate the spatially varying blur kernel. With the addition of contrastive learning, our CDASRN can further distinguish the differences between local blur kernels, greatly improving its practicality. Experiments in various settings show that CDASRN outperforms state-of-the-art methods on both heavily degraded synthetic datasets and real-world datasets.
图像超分辨率 (SR) 通常使用预定义的退化模型来合成退化的低分辨率图像进行训练。当真实退化不符合预定义退化时，现有的 SR 方法不可避免地表现不佳，尤其是在现实世界中。为了解决这个鲁棒性问题，我们提出了一种级联的感知退化盲超分辨率网络 (CDASRN)，它不仅消除了噪声对模糊核估计的影响，而且可以估计空间变化的模糊核。通过添加对比学习，我们的 CDASRN 可以进一步区分局部模糊核之间的差异，大大提高了其实用性。在各种设置下的实验表明，CDASRN 在严重退化的合成数据集和真实世界数据集上的表现均优于最先进的方法。
