Strict Enforcement of Conservation Laws and Invertibility in CNN-Based Super Resolution for Scientific Datasets
This addresses a critical issue for scientific fields relying on image or gridded datasets (e.g., remote sensing, meteorology) by ensuring physical consistency in super-resolution, though it is incremental as it builds on existing CNN methods.
The paper tackles the problem of CNN-based super-resolution methods breaking physical conservation laws when applied to scientific datasets by proposing a 'Downsampling Enforcement' method that ensures high-resolution outputs exactly reproduce low-resolution inputs under 2D-average downsampling. The approach improves training time and performance while maintaining physical consistency across seven modern CNN-based SR schemes on benchmark datasets and applications like weather radar and satellite data.
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.