Solving Image PDEs with a Shallow Network
This work addresses computational inefficiency in PDE-based image processing, offering a flexible solution for various imaging problems, though it appears incremental as it adapts an existing framework to a new application.
The paper tackles the high computational cost of conventional numerical methods for solving PDEs in imaging by applying the shallow learnable filtering framework BLADE, resulting in an efficient and accurate approach that operates reliably at coarse grid resolutions.
Partial differential equations (PDEs) are typically used as models of physical processes but are also of great interest in PDE-based image processing. However, when it comes to their use in imaging, conventional numerical methods for solving PDEs tend to require very fine grid resolution for stability, and as a result have impractically high computational cost. This work applies BLADE (Best Linear Adaptive Enhancement), a shallow learnable filtering framework, to PDE solving, and shows that the resulting approach is efficient and accurate, operating more reliably at coarse grid resolutions than classical methods. As such, the model can be flexibly used for a wide variety of problems in imaging.