Continuous Remote Sensing Image Super-Resolution based on Context Interaction in Implicit Function Space
This addresses the deployment inefficiency for remote sensing applications, though it is incremental as it builds on existing super-resolution methods.
The paper tackles the problem of training and deploying separate models for different resolution magnifications in remote sensing image super-resolution by proposing FunSR, a unified framework that achieves state-of-the-art performance on both fixed and continuous-magnification settings.
Despite its fruitful applications in remote sensing, image super-resolution is troublesome to train and deploy as it handles different resolution magnifications with separate models. Accordingly, we propose a highly-applicable super-resolution framework called FunSR, which settles different magnifications with a unified model by exploiting context interaction within implicit function space. FunSR composes a functional representor, a functional interactor, and a functional parser. Specifically, the representor transforms the low-resolution image from Euclidean space to multi-scale pixel-wise function maps; the interactor enables pixel-wise function expression with global dependencies; and the parser, which is parameterized by the interactor's output, converts the discrete coordinates with additional attributes to RGB values. Extensive experimental results demonstrate that FunSR reports state-of-the-art performance on both fixed-magnification and continuous-magnification settings, meanwhile, it provides many friendly applications thanks to its unified nature.