Deep learning-based blind image super-resolution with iterative kernel reconstruction and noise estimation

TL;DR

This paper introduces IKR-Net, a deep learning model that iteratively estimates blur kernels and noise to enhance blind image super-resolution, effectively handling complex degradations and noise.

Contribution

The paper presents a novel iterative deep learning framework for blind SISR that jointly estimates kernels and noise, improving robustness to complex degradations.

Findings

Achieves state-of-the-art results on blind SISR benchmarks.

Effectively handles noisy images with motion blur.

Provides significant improvements over existing methods.

Abstract

Blind single image super-resolution (SISR) is a challenging task in image processing due to the ill-posed nature of the inverse problem. Complex degradations present in real life images make it difficult to solve this problem using na\"ive deep learning approaches, where models are often trained on synthetically generated image pairs. Most of the effort so far has been focused on solving the inverse problem under some constraints, such as for a limited space of blur kernels and/or assuming noise-free input images. Yet, there is a gap in the literature to provide a well-generalized deep learning-based solution that performs well on images with unknown and highly complex degradations. In this paper, we propose IKR-Net (Iterative Kernel Reconstruction Network) for blind SISR. In the proposed approach, kernel and noise estimation and high-resolution image reconstruction are carried out iteratively using dedicated deep models. The iterative refinement provides significant improvement in both the reconstructed image and the estimated blur kernel even for noisy inputs. IKR-Net provides a generalized solution that can handle any type of blur and level of noise in the input low-resolution image. IKR-Net achieves state-of-the-art results in blind SISR, especially for noisy images with motion blur.