一种基于自样本学习的人脸图像超分辨率复原算法

An algorithm for super-resolution restoration of human faces based on self-example learning

针对人脸图像超分辨率复原问题,提出了一种新的基于自样本学习的超分辨率复原算法。该算法从输入图像本身提取训练样本库,并采用矢量量化的方法对训练样本进行分类。再利用并行设计的多类预测器对每类样本进行学习训练,指导高频信息的估计重建。对来自输入图像本身的自样本训练集合和来自特定训练图像库的特定训练样本集合进行了对比研究。实验结果表明提出算法在图像重建质量和实现速度上都有很好的表现。

The paper proposes a novel super-resolution reconstruction algorithm for human faces. The algorithm extracts training examples from the input image and divides them into several classes using vector quantization. Then, it classifies each patch from a low-resolution image as one of these classes. Each class hag its high-frequency information inferred using a parallel designed multi-class predictor, which is trained using the training samples from the same class. The self-example training set and the specific domain training set were employed in investigation of the impact of the training database. The experimental results showed the superior performance of the proposed method in terms of both the reconstruction quality and runtime.