Real-World Image Super Resolution via Unsupervised Bi-directional Cycle Domain Transfer Learning based Generative Adversarial Network

TL;DR

This paper introduces UBCDTL-GAN, a novel unsupervised GAN framework that improves real-world image super-resolution by transferring low-resolution images to a real-like domain and then super-resolving them, outperforming existing methods.

Contribution

The paper proposes a new unsupervised bi-directional cycle domain transfer learning approach combined with semantic-guided super-resolution for real-world image enhancement.

Findings

Achieves superior super-resolution quality on real-world datasets.

Effectively handles unknown and complex degradation kernels.

Outperforms state-of-the-art methods in unpaired image benchmarks.

Abstract

Deep Convolutional Neural Networks (DCNNs) have exhibited impressive performance on image super-resolution tasks. However, these deep learning-based super-resolution methods perform poorly in real-world super-resolution tasks, where the paired high-resolution and low-resolution images are unavailable and the low-resolution images are degraded by complicated and unknown kernels. To break these limitations, we propose the Unsupervised Bi-directional Cycle Domain Transfer Learning-based Generative Adversarial Network (UBCDTL-GAN), which consists of an Unsupervised Bi-directional Cycle Domain Transfer Network (UBCDTN) and the Semantic Encoder guided Super Resolution Network (SESRN). First, the UBCDTN is able to produce an approximated real-like LR image through transferring the LR image from an artificially degraded domain to the real-world LR image domain. Second, the SESRN has the ability to super-resolve the approximated real-like LR image to a photo-realistic HR image. Extensive experiments on unpaired real-world image benchmark datasets demonstrate that the proposed method achieves superior performance compared to state-of-the-art methods.