Toward Real-world Image Super-resolution via Hardware-based Adaptive Degradation Models

TL;DR

This paper introduces a hardware-aware adaptive degradation model for real-world image super-resolution, improving the realism of low-resolution image simulation and enhancing super-resolution performance on real-world data.

Contribution

It proposes an adaptive blurring layer that incorporates hardware knowledge to better simulate real-world degradations for super-resolution tasks.

Findings

The proposed model estimates low-resolution images more accurately than fixed degradation models.

Super-resolution methods using our degradation model outperform conventional approaches on real-world datasets.

Our approach adapts to different imaging hardware, improving super-resolution results across various devices.

Abstract

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.