Degradation-Guided Meta-Restoration Network for Blind Super-Resolution
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Blind Super-ResolutionImage RestorationSuper-ResolutionSimilar Papers 제목 키워드 기반
RestorerID: Towards Tuning-Free Face Restoration with ID Preservation
Blind face restoration has made great progress in producing high-quality and lifelike images. Yet it remains challenging to preserve the ID information especially when the degradation is heavy. Current reference-guided f…
Blind Face RestorationFace AlignmentINDIGO+: A Unified INN-Guided Probabilistic Diffusion Algorithm for Blind and Non-Blind Image Restoration
Generative diffusion models are becoming one of the most popular prior in image restoration (IR) tasks due to their remarkable ability to generate realistic natural images. Despite achieving satisfactory results, IR meth…
Image RestorationNon-blind Image Restoration Based on Convolutional Neural Network
Blind image restoration processors based on convolutional neural network (CNN) are intensively researched because of their high performance. However, they are too sensitive to the perturbation of the degradation model. T…
Image RestorationFrequency-Aware Guidance for Blind Image Restoration via Diffusion Models
Blind image restoration remains a significant challenge in low-level vision tasks. Recently, denoising diffusion models have shown remarkable performance in image synthesis. Guided diffusion models, leveraging the potent…
Blind Image DeblurringDeblurringDenoisingImage Deblurring+2Taming Generative Diffusion Prior for Universal Blind Image Restoration
Diffusion models have been widely utilized for image restoration. However, previous blind image restoration methods still need to assume the type of degradation model while leaving the parameters to be optimized, limitin…
Image RestorationMathematical Reasoning