IEEE Trans Image Process. 2017 Mar;26(3):1300-1314. doi: 10.1109/TIP.2017.2651411. Epub 2017 Jan 10.
Super-resolution (SR) has become more vital, because of its capability to generate high-quality ultra-high definition (UHD) high-resolution (HR) images from low-resolution (LR) input images. Conventional SR methods entail high computational complexity, which makes them difficult to be implemented for up-scaling of full-high-definition input images into UHD-resolution images. Nevertheless, our previous super-interpolation (SI) method showed a good compromise between Peak-Signal-to-Noise Ratio (PSNR) performances and computational complexity. However, since SI only utilizes simple linear mappings, it may fail to precisely reconstruct HR patches with complex texture. In this paper, we present a novel SR method, which inherits the large-to-small patch conversion scheme from SI but uses global regression based on local linear mappings (GLM). Thus, our new SR method is called GLM-SI. In GLM-SI, each LR input patch is divided into 25 overlapped subpatches. Next, based on the local properties of these subpatches, 25 different local linear mappings are applied to the current LR input patch to generate 25 HR patch candidates, which are then regressed into one final HR patch using a global regressor. The local linear mappings are learned cluster-wise in our off-line training phase. The main contribution of this paper is as follows: Previously, linear-mapping-based conventional SR methods, including SI only used one simple yet coarse linear mapping to each patch to reconstruct its HR version. On the contrary, for each LR input patch, our GLM-SI is the first to apply a combination of multiple local linear mappings, where each local linear mapping is found according to local properties of the current LR patch. Therefore, it can better approximate nonlinear LR-to-HR mappings for HR patches with complex texture. Experiment results show that the proposed GLM-SI method outperforms most of the state-of-the-art methods, and shows comparable PSNR performance with much lower computational complexity when compared with a super-resolution method based on convolutional neural nets (SRCNN15). Compared with the previous SI method that is limited with a scale factor of 2, GLM-SI shows superior performance with average 0.79 dB higher in PSNR, and can be used for scale factors of 3 or higher.
超分辨率（SR）变得越来越重要，因为它能够从低分辨率（LR）输入图像生成高质量的超高清晰度（UHD）高分辨率（HR）图像。传统的 SR 方法需要较高的计算复杂度，这使得它们难以用于将全高清输入图像上采样到 UHD 分辨率图像。然而，我们之前的超插值（SI）方法在峰值信噪比（PSNR）性能和计算复杂度之间取得了很好的折衷。然而，由于 SI 仅利用简单的线性映射，它可能无法精确地重建具有复杂纹理的 HR 补丁。在本文中，我们提出了一种新的 SR 方法，它继承了 SI 的大到小补丁转换方案，但使用基于局部线性映射的全局回归（GLM）。因此，我们的新 SR 方法称为 GLM-SI。在 GLM-SI 中，每个 LR 输入补丁被划分为 25 个重叠的子补丁。接下来，根据这些子补丁的局部特性，应用 25 个不同的局部线性映射来生成 25 个 HR 补丁候选者，然后使用全局回归器将它们回归为一个最终的 HR 补丁。局部线性映射在我们的离线训练阶段按聚类进行学习。本文的主要贡献如下：以前，基于线性映射的传统 SR 方法，包括 SI，仅对每个补丁使用一个简单但粗糙的线性映射来重建其 HR 版本。相反，对于每个 LR 输入补丁，我们的 GLM-SI 首先应用一组多个局部线性映射，其中每个局部线性映射是根据当前 LR 补丁的局部特性找到的。因此，它可以更好地逼近具有复杂纹理的 HR 补丁的非线性 LR 到 HR 映射。实验结果表明，所提出的 GLM-SI 方法优于大多数最先进的方法，并且与基于卷积神经网络的 SR 方法（SRCNN15）相比，具有更低的计算复杂度和相当的 PSNR 性能。与之前的 SI 方法相比，它的比例因子为 2，GLM-SI 具有更高的 PSNR，平均提高 0.79dB，并且可以用于比例因子为 3 或更高。
