论文标题
严格执行保护法和基于CNN的科学数据集的超级分辨率的可逆性
Strict Enforcement of Conservation Laws and Invertibility in CNN-Based Super Resolution for Scientific Datasets
论文作者
论文摘要
最近，深度卷积神经网络（CNN）彻底改变了图像超分辨率（SR），极大地超过了过去的方法来增强图像分辨率。对于许多涉及图像或网格数据集的科学领域，它们可能是一个福音：卫星遥感，雷达气象，医学成像，数值建模等。不幸的是，尽管SR-CNN会产生令人信服的令人信服的输出，但它们可能会在科学数据集中应用物理保护法。在这里，提出了一种SR-CNN中``降低采样执法''的方法。一种可区分的操作员得出的是，当应用于CNN的最终传输功能时，将高分辨率输出准确地重现低分辨率的低分辨率输入，以在2d平均下降范围内进行较低的sr sr sremes sr shem sremes of Sremess sre sremes sremes sremess sre sremess of Srem shem sremess sre condection。还显示了数据集以及对天气雷达，卫星成像仪和气候模型数据的应用程序。
Recently, deep Convolutional Neural Networks (CNNs) have revolutionized image super-resolution (SR), dramatically outperforming past methods for enhancing image resolution. They could be a boon for the many scientific fields that involve image or gridded datasets: satellite remote sensing, radar meteorology, medical imaging, numerical modeling etc. Unfortunately, while SR-CNNs produce visually compelling outputs, they may break physical conservation laws when applied to scientific datasets. Here, a method for ``Downsampling Enforcement" in SR-CNNs is proposed. A differentiable operator is derived that, when applied as the final transfer function of a CNN, ensures the high resolution outputs exactly reproduce the low resolution inputs under 2D-average downsampling while improving performance of the SR schemes. The method is demonstrated across seven modern CNN-based SR schemes on several benchmark image datasets, and applications to weather radar, satellite imager, and climate model data are also shown. The approach improves training time and performance while ensuring physical consistency between the super-resolved and low resolution data.
