面向真实世界图像超分辨率的多感知特征学习
Learning from Multi-Perception Features for Real-Word Image Super-resolution
AI总结：
本文提出 MPF-Net，通过多感知特征提取模块和跨感知模块融合多样化感知信息，并引入对比正则化项，显著提升真实世界图像超分辨率性能。
摘要：
目前，解决真实世界图像超分辨率问题有两种流行方法：基于退化估计的方法和盲方法。然而，基于退化估计的方法在估计退化时可能不准确，使其不太适用于真实世界的低分辨率图像。另一方面，盲方法通常受限于其固定的单一感知信息，这阻碍了它们处理多样化感知特性的能力。为克服这一局限，我们提出了一种名为 MPF-Net 的新型超分辨率方法，该方法利用输入图像的多重感知特征。我们的方法引入了一个多感知特征提取（MPFE）模块来提取多样化的感知信息，并设计了一系列新的跨感知模块（CPB）来结合这些信息以实现有效的超分辨率重建。此外，我们引入了一个对比正则化项（CR），通过使用新生成的高分辨率（HR）和低分辨率（LR）图像作为真实高分辨率（HR）的正样本和负样本，提高模型的学习能力。在具有挑战性的真实世界超分辨率数据集上的实验结果表明，我们的方法在定性和定量指标上都显著优于现有的最先进方法。
英文摘要：
Currently, there are two popular approaches for addressing real-world image super-resolution problems: degradation-estimation-based and blind-based methods. However, degradation-estimation-based methods may be inaccurate in estimating the degradation, making them less applicable to real-world LR images. On the other hand, blind-based methods are often limited by their fixed single perception information, which hinders their ability to handle diverse perceptual characteristics. To overcome this limitation, we propose a novel SR method called MPF-Net that leverages multiple perceptual features of input images. Our method incorporates a Multi-Perception Feature Extraction (MPFE) module to extract diverse perceptual information and a series of newly-designed Cross-Perception Blocks (CPB) to combine this information for effective super-resolution reconstruction. Additionally, we introduce a contrastive regularization term (CR) that improves the model's learning capability by using newly generated HR and LR images as positive and negative samples for ground truth HR. Experimental results on challenging real-world SR datasets demonstrate that our approach significantly outperforms existing state-of-the-art methods in both qualitative and quantitative measures.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
