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

10/20/2021
by   Rui Ma, et al.
0

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.

READ FULL TEXT

page 4

page 5

page 9

research
09/08/2021

Toward Real-World Super-Resolution via Adaptive Downsampling Models

Most image super-resolution (SR) methods are developed on synthetic low-...
research
06/13/2022

Learning a Degradation-Adaptive Network for Light Field Image Super-Resolution

Recent years have witnessed the great advances of deep neural networks (...
research
11/05/2021

Frequency-Aware Physics-Inspired Degradation Model for Real-World Image Super-Resolution

Current learning-based single image super-resolution (SISR) algorithms u...
research
04/19/2021

Kernel Agnostic Real-world Image Super-resolution

Recently, deep neural network models have achieved impressive results in...
research
03/02/2022

Self-Supervised Learning for Real-World Super-Resolution from Dual Zoomed Observations

In this paper, we consider two challenging issues in reference-based sup...
research
12/15/2022

DCS-RISR: Dynamic Channel Splitting for Efficient Real-world Image Super-Resolution

Real-world image super-resolution (RISR) has received increased focus fo...
research
04/06/2019

Camera Lens Super-Resolution

Existing methods for single image super-resolution (SR) are typically ev...

Please sign up or login with your details

Forgot password? Click here to reset