Benchmarking Super-Resolution Algorithms on Real Data
This provides a standardized benchmark for researchers and practitioners in computer vision to evaluate super-resolution methods on real data, though it is incremental as it focuses on data creation rather than new algorithms.
The paper tackled the lack of comparative validation for super-resolution algorithms under practical conditions by introducing the SupER database with over 20k real low-resolution images and high-resolution ground truth from 14 scenes, and used it to benchmark 15 algorithms, analyzing accuracy and robustness in realistic scenarios.
Over the past decades, various super-resolution (SR) techniques have been developed to enhance the spatial resolution of digital images. Despite the great number of methodical contributions, there is still a lack of comparative validations of SR under practical conditions, as capturing real ground truth data is a challenging task. Therefore, current studies are either evaluated 1) on simulated data or 2) on real data without a pixel-wise ground truth. To facilitate comprehensive studies, this paper introduces the publicly available Super-Resolution Erlangen (SupER) database that includes real low-resolution images along with high-resolution ground truth data. Our database comprises image sequences with more than 20k images captured from 14 scenes under various types of motions and photometric conditions. The datasets cover four spatial resolution levels using camera hardware binning. With this database, we benchmark 15 single-image and multi-frame SR algorithms. Our experiments quantitatively analyze SR accuracy and robustness under realistic conditions including independent object and camera motion or photometric variations.