论文标题
随机频率掩盖以改善超分辨率和降解网络
Stochastic Frequency Masking to Improve Super-Resolution and Denoising Networks
论文作者
论文摘要
超分辨率和denoising是不适合但基本的图像恢复任务。在盲目的环境中，降解内核或噪声水平未知。这使得恢复更具挑战性，特别是对于基于学习的方法而言，它们倾向于过分地融入培训期间的退化。我们在频域中介绍了降解内核过度拟合的分析，并引入了有条件的学习观点，该视角既扩展到超分辨率和脱氧。在我们的公式的基础上，我们提出了用于训练正规化网络并解决过度拟合问题的随机频率掩盖。我们的技术通过不同的合成核，真正的超分辨率，盲型高斯denoising和现实图像降解来改善盲目超级分辨率的最先进方法。
Super-resolution and denoising are ill-posed yet fundamental image restoration tasks. In blind settings, the degradation kernel or the noise level are unknown. This makes restoration even more challenging, notably for learning-based methods, as they tend to overfit to the degradation seen during training. We present an analysis, in the frequency domain, of degradation-kernel overfitting in super-resolution and introduce a conditional learning perspective that extends to both super-resolution and denoising. Building on our formulation, we propose a stochastic frequency masking of images used in training to regularize the networks and address the overfitting problem. Our technique improves state-of-the-art methods on blind super-resolution with different synthetic kernels, real super-resolution, blind Gaussian denoising, and real-image denoising.
