Real-scene image super-resolution aims to restore real-world low-resolution images into their high-quality versions. A typical RealSR framework usually includes the optimization of multiple criteria which are designed for different image properties, by making the implicit assumption that the ground-truth images can provide a good trade-off between different criteria. However, this assumption could be easily violated in practice due to the inherent contrastive relationship between different image properties. Contrastive learning (CL) provides a promising recipe to relieve this problem by learning discriminative features using the triplet contrastive losses. Though CL has achieved significant success in many computer vision tasks, it is non-trivial to introduce CL to RealSR due to the difficulty in defining valid positive image pairs in this case. Inspired by the observation that the contrastive relationship could also exist between the criteria, in this work, we propose a novel training paradigm for RealSR, named Criteria Comparative Learning (Cria-CL), by developing contrastive losses defined on criteria instead of image patches. In addition, a spatial projector is proposed to obtain a good view for Cria-CL in RealSR. Our experiments demonstrate that compared with the typical weighted regression strategy, our method achieves a significant improvement under similar parameter settings.
翻译:真实摄氏图像超分辨率的超真镜图像旨在将真实世界低分辨率图像恢复到高质量的版本中。典型的 RealSR框架通常包括优化针对不同图像属性设计的多重标准,其方式是隐含地假设地面真实图像能够在不同标准之间提供良好的权衡。然而,由于不同图像属性之间的内在对比性关系,这一假设在实际中很容易被违反。对比性学习(CL)提供了一种很有希望的方法,通过利用三重对比性损失学习歧视性特征来缓解这一问题。虽然CL在许多计算机愿景任务中取得了巨大成功,但引入CL到RealSR并不具有三重性,因为在本案中很难界定有效的正对图像。我们观察到,在标准之间也可能存在对比性关系,因此,我们建议为RealSR,称为标准比较学习(Cria-CL),通过在标准上而不是图像补差上界定的对比性损失来形成新的培训模式。此外,还提议空间投影仪在RealSR中为CL,为CL设定一个良好的视角,因为在此案中很难界定有效的正态,因此,引入CL到Real-CL是非三重度的。我们的实验性参数,因此,因此,我们提出一种与典型的对比性对比性对比性对比性对比性对比性对比性对比性比较性研究制制制制制制的模型的模型的实验显示。