ICF-SRSR: Invertible scale-Conditional Function for Self-Supervised Real-world Single Image Super-Resolution

TL;DR

This paper introduces ICF-SRSR, a self-supervised framework for real-world single image super-resolution that uses an invertible scale-conditional function to generate training pairs without needing paired data, improving robustness and performance.

Contribution

The paper proposes a novel invertible scale-conditional function and a self-supervised framework for real-world SISR, eliminating the need for paired training data and enhancing robustness.

Findings

Outperforms existing methods in real-world scenarios

Generates realistic LR-HR pairs for training

Achieves comparable results to state-of-the-art supervised methods

Abstract

Single image super-resolution (SISR) is a challenging ill-posed problem that aims to up-sample a given low-resolution (LR) image to a high-resolution (HR) counterpart. Due to the difficulty in obtaining real LR-HR training pairs, recent approaches are trained on simulated LR images degraded by simplified down-sampling operators, e.g., bicubic. Such an approach can be problematic in practice because of the large gap between the synthesized and real-world LR images. To alleviate the issue, we propose a novel Invertible scale-Conditional Function (ICF), which can scale an input image and then restore the original input with different scale conditions. By leveraging the proposed ICF, we construct a novel self-supervised SISR framework (ICF-SRSR) to handle the real-world SR task without using any paired/unpaired training data. Furthermore, our ICF-SRSR can generate realistic and feasible LR-HR pairs, which can make existing supervised SISR networks more robust. Extensive experiments demonstrate the effectiveness of the proposed method in handling SISR in a fully self-supervised manner. Our ICF-SRSR demonstrates superior performance compared to the existing methods trained on synthetic paired images in real-world scenarios and exhibits comparable performance compared to state-of-the-art supervised/unsupervised methods on public benchmark datasets.