Robust super resolution of compressed video

Robust super resolution of compressed video
复制标题

压缩视频的强大超分辨率

DOI:
10.1007/s00371-011-0666-8
复制
发表时间:
2012-01
期刊:
影响因子:
3.5
通讯作者:
Tong, Ruofeng
Tong, Ruofeng
中科院分区:
计算机科学3区
文献类型:
--
作者:
Zhang, Xiaohong;Tang, Min;Tong, Ruofeng

文献摘要

参考文献

被引文献

相似文献

提出了一种从压缩低分辨率视频序列中恢复高频信息的鲁棒算法。当LR序列中的运动是简单的时,先前的超分辨率(SR)方法已经成功地在分辨率增强上。然而,当运动是复杂的,新的伪影将被引入到SR处理中。为了解决这个问题,我们开发了一个强大的贝叶斯SR算法两个步骤。我们首先单独隔离的帧,以获得其相应的初始SR解决方案的贝叶斯框架内。其次,利用一个鲁棒的代价函数来拒绝离群值和噪声,最终的SR图像是由多个LR帧获得的。同时,我们施加的约束,即高分辨率(HR)图像的梯度分布应等于相应的解压缩LR图像之一,锐化结果的边缘。由于这些步骤,我们能够产生高质量的去模糊结果,这表明抑制了高频伪影和更少的振铃伪影,具有更高的峰值信噪比(PSNR)。
This paper presents a robust algorithm to recover high-frequency information from compressed low-resolution (LR) video sequences. Previous super-resolution (SR) approaches have succeeded in resolution enhancement when the motion in the LR sequence is simple. However, when the motion is complex, new artifacts will be introduced in the SR processing. To solve this problem, we develop a robust Bayesian SR algorithm with two steps. We first isolate the frames individually to get their corresponding initial SR solutions within the Bayesian framework. Secondly, with a robust cost function to reject outliers and noise, final SR images are achieved with multiple LR frames. In the mean time, we impose the constraint that the distribution of high-resolution (HR) image gradient should be equal to one of the corresponding decompressed LR images to sharpen the edges of the results. As a result of these steps, we are able to produce high-quality deblurred results, which show a suppressing of high-frequency artifacts and less ringing artifacts, with a higher peak signal-to-noise ratio (PSNR).
DOI: 10.1109/76.999200
发表时间: 2002-04
期刊: IEEE Trans. Circuits Syst. Video Technol.
影响因子: --
作者:
Y. Altunbasak;Andrew J. Patti;R. Mersereau
通讯作者: Y. Altunbasak;Andrew J. Patti;R. Mersereau
DOI: 10.1002/ima.20008
发表时间: 2004
影响因子: 3.3
作者:
Luis D. Alvarez;J. Mateos;R. Molina;A. Katsaggelos
通讯作者: Luis D. Alvarez;J. Mateos;R. Molina;A. Katsaggelos
DOI: 10.1007/0-306-47004-7_9
发表时间: 2002
期刊: --
影响因子: --
作者:
C. A. Segall;A. Katsaggelos;R. Molina;J. Mateos
通讯作者: C. A. Segall;A. Katsaggelos;R. Molina;J. Mateos
DOI: 10.1631/fitee.1700813
发表时间: 2018-01-01
影响因子: 3
作者:
Yu, Bin;Kumbier, Karl
通讯作者: Kumbier, Karl
DOI: --
发表时间: 2003
期刊: --
影响因子: --
作者:
Charles M. Bishop;A. Blake;B. Marthi
通讯作者: Charles M. Bishop;A. Blake;B. Marthi