摘要
Collecting amounts of distorted/clean image pairs in the real world is non-trivial,which severely limits the practical application of these supervised learning-based methods to real-world image super-resolution(RealSR).Previous works usually address this problem by leveraging unsupervised learning-based technologies to alleviate the dependency on paired training samples.However,these methods typically suffer from unsatisfactory texture synthesis due to the lack of supervision of clean images.To overcome this problem,we are the first to take a close look at the under-explored direction for RealSR,i.e.,few-shot real-world image super-resolution,which aims to tackle the challenging RealSR problem with few-shot distorted/clean image pairs.Under this brand-new scenario,we propose distortion relation guided transfer learning(DRTL)for the few-shot RealSR by transferring the rich restoration knowledge from auxiliary distortions(i.e.,synthetic distortions)to the target RealSR under the guidance of the distortion relation.Concretely,DRTL builds a knowledge graph to capture the distortion relation between auxiliary distortions and target distortion(i.e.,real distortions in RealSR).Based on the distortion relation,DRTL adopts a gradient reweighting strategy to guide the knowledge transfer process between auxiliary distortions and target distortions.In this way,DRTL is able to quickly learn the most relevant knowledge from the synthetic distortions for the target distortion.We instantiate DRTL with two commonly-used transfer learning paradigms,including pretraining and meta-learning pipelines,to realize a distortion relation-aware few-shot RealSR.Extensive experiments on multiple benchmarks and thorough ablation studies demonstrate the effectiveness of our DRTL.
在真实世界中收集大量的失真/清晰图像对并非易事,这严重限制了基于监督学习的方法在真实场景图像超分辨率(RealSR)任务中的实际应用。以往的研究通常利用无监督学习方法来缓解对成对训练样本的依赖。然而,由于缺乏高清图像的监督,这些方法往往在纹理合成方面表现不佳。为了解决这一问题,我们首次聚焦于一个尚未被充分探索的研究方向,即少样本真实场景图像超分辨(Few-shot RealSR),其目标是利用仅有的少量失真/清晰图像对解决具有挑战性的真实场景图像超分辨率任务。在这一研究方向中,我们提出了基于失真关系引导的迁移学习方法(distortion relation guided transfer learning,DRTL),该方法借助辅助失真(即合成失真)中丰富的图像复原知识,在失真关系的引导下迁移到目标复原任务中。具体来说,DRTL构建了一个知识图谱,以捕捉辅助失真与目标失真(即RealSR中的真实失真)之间的关系。在此基础上,DRTL采用了一种优化梯度重加权策略,以引导辅助失真与目标失真之间的复原知识迁移过程。通过这种方式,DRTL能够快速从合成失真中学习到对目标失真最相关的知识。我们将DRTL应用于两种常用的迁移学习范式中,包括预训练(pretraining)和元学习(meta-learning)范式,从而实现了一个具备失真关系感知能力的少样本真实场景图像超分框架。大量的基准测试实验及详细的消融分析充分验证了DRTL的有效性。
基金
supported by the National Natural Science Foundation of China(623B2098,62021001,62371434)
the Postdoctoral Fellowship Program of CPSF(GZC20252293)
the China Postdoctoral Science Foundation–Anhui Joint Support Program(2024T017AH)
Anhui Postdoctoral Scientific Research Program Foundation(2025A1015).
