arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2311.02254eess.IVcs.CVcs.GR
收藏

面向含噪图像的基于学习且保质量的超分辨率方法

Learning-Based and Quality Preserving Super-Resolution of Noisy Images

CNR-IMATI(意大利国家研究委员会 IMATI 研究所)

Simone Cammarasana, Giuseppe Patanè

AI总结:

针对现有超分辨率方法未考虑噪声、易产生伪影的问题,提出一种基于学习的保质量超分辨率方法,可保留图像属性、减少伪影,在2倍上采样高斯噪声图像任务中PSNR达23.81,优于同类学习方法,效果与传统方法相当。

摘要:

多项应用需要实现含噪图像的超分辨率,同时保留几何与纹理特征。现有最先进的超分辨率方法未考虑噪声影响,通常会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,该方法可应对噪声存在的情况,同时保留输入图像的属性——以定量指标(如归一化互相关、归一化均方误差、峰值信噪比、基于结构相似性的特征相似度、通用图像质量指数)衡量。我们训练网络对低分辨率含噪图像进行上采样,同时保留其属性。我们在TOP500榜单中位列第26位的Cineca Marconi100集群上开展测试。实验结果表明,我们的方法性能优于基于学习的方法,与传统方法结果相当,能够保留输入图像的轮廓、亮度和纹理等属性,同时减少伪影。作为平均定量指标,在2倍上采样因子的高斯噪声图像超分辨率任务中,我们的方法PSNR值为23.81。相比之下,已有研究的PSNR值分别为23.09(传统方法)和21.78(基于学习的方法)。我们的基于学习且保质量的超分辨率方法,在不同噪声类型和上采样因子下,相较于现有最先进方法,提升了含噪图像的高分辨率预测效果。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑