Toward Real-world Image Super-resolution via Hardware-based Adaptive Degradation Models
This work addresses the challenge of applying super-resolution methods to real-world images, which often fail due to deviations from synthetic degradation models, by incorporating hardware knowledge for more accurate simulations.
The paper tackles the problem of real-world image super-resolution by proposing a supervised method that simulates unknown degradation processes using hardware-based adaptive degradation models, resulting in more accurate low-resolution image estimation and improved reconstruction performance compared to conventional approaches.
Most single image super-resolution (SR) methods are developed on synthetic low-resolution (LR) and high-resolution (HR) image pairs, which are simulated by a predetermined degradation operation, e.g., bicubic downsampling. However, these methods only learn the inverse process of the predetermined operation, so they fail to super resolve the real-world LR images; the true formulation deviates from the predetermined operation. To address this problem, we propose a novel supervised method to simulate an unknown degradation process with the inclusion of the prior hardware knowledge of the imaging system. We design an adaptive blurring layer (ABL) in the supervised learning framework to estimate the target LR images. The hyperparameters of the ABL can be adjusted for different imaging hardware. The experiments on the real-world datasets validate that our degradation model can estimate LR images more accurately than the predetermined degradation operation, as well as facilitate existing SR methods to perform reconstructions on real-world LR images more accurately than the conventional approaches.