Degradation-Guided Meta-Restoration Network for Blind Super-Resolution
This addresses the problem of recovering high-quality images from real-world low-resolution inputs with unknown degradations for computer vision applications, representing a novel method for a known bottleneck.
The paper tackles blind super-resolution by proposing a network that estimates degradations and adapts restoration parameters on-the-fly, outperforming state-of-the-art methods by a large margin on three benchmarks and validating superiority in a user study with 16 subjects.
Blind super-resolution (SR) aims to recover high-quality visual textures from a low-resolution (LR) image, which is usually degraded by down-sampling blur kernels and additive noises. This task is extremely difficult due to the challenges of complicated image degradations in the real-world. Existing SR approaches either assume a predefined blur kernel or a fixed noise, which limits these approaches in challenging cases. In this paper, we propose a Degradation-guided Meta-restoration network for blind Super-Resolution (DMSR) that facilitates image restoration for real cases. DMSR consists of a degradation extractor and meta-restoration modules. The extractor estimates the degradations in LR inputs and guides the meta-restoration modules to predict restoration parameters for different degradations on-the-fly. DMSR is jointly optimized by a novel degradation consistency loss and reconstruction losses. Through such an optimization, DMSR outperforms SOTA by a large margin on three widely-used benchmarks. A user study including 16 subjects further validates the superiority of DMSR in real-world blind SR tasks.