Fusion of Deep and Non-Deep Methods for Fast Super-Resolution of Satellite Images
This addresses the need for faster super-resolution in the commercial satellite industry, where processing large images quickly is crucial, though it is an incremental improvement over existing methods.
The paper tackles the problem of slow super-resolution for large satellite images by proposing a framework that selectively applies deep models to structure-rich regions and non-deep methods to non-salient regions, resulting in a substantial decrease in inference time while maintaining similar performance to existing deep methods on metrics like PSNR, MSE, and SSIM.
In the emerging commercial space industry there is a drastic increase in access to low cost satellite imagery. The price for satellite images depends on the sensor quality and revisit rate. This work proposes to bridge the gap between image quality and the price by improving the image quality via super-resolution (SR). Recently, a number of deep SR techniques have been proposed to enhance satellite images. However, none of these methods utilize the region-level context information, giving equal importance to each region in the image. This, along with the fact that most state-of-the-art SR methods are complex and cumbersome deep models, the time taken to process very large satellite images can be impractically high. We, propose to handle this challenge by designing an SR framework that analyzes the regional information content on each patch of the low-resolution image and judiciously chooses to use more computationally complex deep models to super-resolve more structure-rich regions on the image, while using less resource-intensive non-deep methods on non-salient regions. Through extensive experiments on a large satellite image, we show substantial decrease in inference time while achieving similar performance to that of existing deep SR methods over several evaluation measures like PSNR, MSE and SSIM.