Several applications require the super-resolution of noisy images and the preservation of geometrical and texture features. State-of-the-art super-resolution methods do not account for noise and generally enhance the output image's artefacts (e.g., aliasing, blurring). We propose a learning-based method that accounts for the presence of noise and preserves the properties of the input image, as measured by quantitative metrics (e.g., normalised crossed correlation, normalised mean squared error, peak-signal-to-noise-ration, structural similarity feature-based similarity, universal image quality). We train our network to up-sample a low-resolution noisy image while preserving its properties. We perform our tests on the Cineca Marconi100 cluster, at the 26th position in the top500 list. The experimental results show that our method outperforms learning-based methods, has comparable results with standard methods, preserves the properties of the input image as contours, brightness, and textures, and reduces the artefacts. As average quantitative metrics, our method has a PSNR value of 23.81 on the super-resolution of Gaussian noise images with a 2X up-sampling factor. In contrast, previous work has a PSNR value of 23.09 (standard method) and 21.78 (learning-based method). Our learning-based and quality-preserving super-resolution improves the high-resolution prediction of noisy images with respect to state-of-the-art methods with different noise types and up-sampling factors.

翻译：多项应用要求对噪声图像进行超分辨率处理，同时保持几何与纹理特征。现有超分辨率方法未考虑噪声影响，且通常加剧输出图像的伪影（如混叠、模糊）。我们提出一种基于学习的方法，该方法兼顾噪声存在性，并通过量化指标（如归一化互相关、归一化均方误差、峰值信噪比、结构相似性特征相似度、通用图像质量）保持输入图像属性。训练网络对低分辨率噪声图像进行上采样的同时保持其属性。我们在Cineca Marconi100集群（位列top500第26位）上进行测试。实验结果表明，本方法优于基于学习的方法，与传统方法效果相当，能保持输入图像的轮廓、亮度和纹理等属性，同时减少伪影。平均量化指标显示：在2倍上采样因子的高斯噪声图像超分辨率任务中，本方法的PSNR值为23.81，而现有方法中传统方法为23.09、基于学习方法为21.78。与采用不同噪声类型和上采样因子的现有技术相比，本方法显著提升了噪声图像的高分辨率预测效果。