Shi Jingang, Liu Xin, Zong Yuan, Qi Chun, Zhao Guoying
IEEE Trans Image Process. 2018 Mar 9. doi: 10.1109/TIP.2018.2813163.
In this paper, we propose two novel regularization models in patch-wise and pixel-wise respectively, which are efficient to reconstruct high-resolution (HR) face image from low-resolution (LR) input. Unlike the conventional patch-based models which depend on the assumption of local geometry consistency in LR and HR spaces, the proposed method directly regularizes the relationship between the target patch and corresponding training set in the HR space. It avoids to deal with the tough problem of preserving local geometry in various resolutions. Taking advantage of kernel function in efficiently describing intrinsic features, we further conduct the patch-based reconstruction model in the high-dimensional kernel space for capturing nonlinear characteristics. Meanwhile, a pixel-based model is proposed to regularize the relationship of pixels in the local neighborhood, which can be employed to enhance the fuzzy details in the target HR face image. It privileges the reconstruction of pixels along the dominant orientation of structure, which is useful for preserving high-frequency information on complex edges. Finally, we combine the two reconstruction models into a unified framework. The output HR face image can be finally optimized by performing an iterative procedure. Experimental results demonstrate that the proposed face hallucination method produces superior performance than the state-of-the-art methods.
在本文中，我们分别提出了两种新颖的正则化模型，一种是基于块的，另一种是基于像素的，它们能够有效地从低分辨率（LR）输入重建高分辨率（HR）人脸图像。与传统的基于块的模型不同，传统模型依赖于LR和HR空间中局部几何一致性的假设，而我们提出的方法直接在HR空间中对目标块与相应训练集之间的关系进行正则化。它避免了处理在各种分辨率下保留局部几何的棘手问题。利用核函数有效描述内在特征的优势，我们进一步在高维核空间中进行基于块的重建模型，以捕捉非线性特征。同时，提出了一种基于像素的模型来正则化局部邻域中像素的关系，该模型可用于增强目标HR人脸图像中的模糊细节。它优先沿结构的主导方向重建像素，这对于保留复杂边缘上的高频信息很有用。最后，我们将这两种重建模型组合成一个统一的框架。最终通过执行迭代过程来优化输出的HR人脸图像。实验结果表明，所提出的人脸超分辨率方法比现有方法具有更优的性能。
