Video super-resolution using an adaptive superpixel-guided auto-regressive model
Video super-resolution using an adaptive superpixel-guided auto-regressive model
复制标题
DOI：
10.1016/j.patcog.2015.08.008
复制
发表时间：
2016-03
期刊：
影响因子：
--
通讯作者：
Kun Li;Yanming Zhu;Jingyu Yang;Jianmin Jiang
中科院分区：
文献类型：
--
作者：
Kun Li;Yanming Zhu;Jingyu Yang;Jianmin Jiang
提出了一种基于自适应超像素引导自回归（AR）模型的视频超分辨率方法。关键帧的自动选择和超分辨率的稀疏回归方法。非关键帧通过利用时空相关性来超分辨：时间相关性通过光流方法来利用，而空间相关性通过超像素引导的AR模型来建模。实验结果表明，该方法在主观视觉质量和客观峰值信噪比（PSNR）方面都优于现有方法。该方法计算量小，适合于实际应用。
This paper proposes a video super-resolution method based on an adaptive superpixel-guided auto-regressive (AR) model. Key-frames are automatically selected and super-resolved by a sparse regression method. Non-key-frames are super-resolved by exploiting the spatio-temporal correlations: the temporal correlation is exploited by an optical flow method while the spatial correlation is modeled by a superpixel-guided AR model. Experimental results show that the proposed method outperforms state-of-the-art methods in terms of both subjective visual quality and objective peak signal-to-noise ratio (PSNR). The proposed method requires less computation and is suitable for practical applications.