应用空时相关性的单视频超分辨率算法

Single Video Super-Resolution by Using Spatio-temporal Correlation

已有的单视频超分辨率算法大多基于精确的运动估计,当运动估计不准确时,超分辨率结果中将出现失真现象。针对这一问题,提出一种新的单视频超分辨率算法。通过三维非局部均值约束模型表征视频内的空时相关性,同时采用总变分模型表征视频帧内局部相似性。最后,为了求解所建立的最优化问题,提出了基于split-Bregman方法的快速迭代算法。实验结果表明,与同类算法相比,提出的算法获得了最佳客观及主观结果。

The traditional reconstruction-based single video super-resolution algorithms are able to solve the vidco super-reso-lution problem well.However,the existing algorithms strongly rely on the accuracy of the motion estimation.When the estimation is not accurate enough,some artifacts will appear in the super-resolved outcome.This paper proposes a new single video super-resolution algorithm to solve this problem.To this end,the three-dimensional non-local means is used to explore the inter-frame and intra-frame non-local structural property,and the total variation model is utilized to describe the local structural property.Finally,to solve the established optimization problem,a split-Bregman method-based iteration is proposed.The experimental results demonstrate the effectiveness of the proposed algorithm.Compared with other algorithms,the proposed one is able to achieve better subjective and objective results.