Two Heads Better Than One: Dual Degradation Representation for Blind Super-Resolution

Previous methods have demonstrated remarkable performance in single image super-resolution (SISR) tasks with known and fixed degradation (e.g., bicubic downsampling). However, when the actual degradation deviates from these assumptions, these methods may experience significant declines in performance. In this paper, we propose a Dual Branch Degradation Extractor Network to address the blind SR problem. While some blind SR methods assume noisefree degradation and others do not explicitly consider the presence of noise in the degradation model, our approach predicts two unsupervised degradation embeddings that represent blurry and noisy information. The SR network can then be adapted to blur embedding and noise embedding in distinct ways. Furthermore, we treat the degradation extractor as a regularizer to capitalize on differences between SR and HR images. Extensive experiments on several benchmarks demonstrate our method achieves SOTA performance in the blind SR problem.

1. Introduction

SISR tasks aim to reconstruct high-resolution (HR) images from low-resolution (LR) inputs. While significant progress has been made in SISR, real-world degradation is often diverse and unknown, leading to performance drops in blind super-resolution (blind SR) settings. To tackle this issue, blind SR methods [1, 2, 3, 4, 5, 6, 7, 8, 9] have been proposed to handle unknown and diverse degradation.