arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2103.15683eess.IVcs.CV
收藏

全知视频超分辨率

Omniscient Video Super-Resolution

Wuhan University(武汉大学);Harbin Institute of Technology(哈尔滨工业大学);Wuhan Institute of Technology(武汉工程大学)

Peng Yi, Zhongyuan Wang, Kui Jiang, Junjun Jiang, Tao Lu, Xin Tian, Jiayi Ma

摘要:

最近的视频超分辨率(SR)方法要么采用迭代的方式来处理来自时间滑动窗口的低分辨率(LR)帧,要么利用先前估计的SR输出来帮助递归地重建当前帧。一些研究试图将这两种结构结合起来,形成一个混合框架,但未能充分发挥它的作用。在本文中,我们提出了一个全知的框架,不仅利用以前的SR输出,而且还利用SR输出从现在和未来。全知框架更具有一般性,因为迭代框架、递归框架和混合框架可以被视为其特例。建议的全知框架,使发电机的行为比其他框架下的同行。在公开数据集上的大量实验表明,该方法在客观度量、主观视觉效果和复杂度方面均优于现有方法。我们的代码将被公开。

英文摘要:

Most recent video super-resolution (SR) methods either adopt an iterative manner to deal with low-resolution (LR) frames from a temporally sliding window, or leverage the previously estimated SR output to help reconstruct the current frame recurrently. A few studies try to combine these two structures to form a hybrid framework but have failed to give full play to it. In this paper, we propose an omniscient framework to not only utilize the preceding SR output, but also leverage the SR outputs from the present and future. The omniscient framework is more generic because the iterative, recurrent and hybrid frameworks can be regarded as its special cases. The proposed omniscient framework enables a generator to behave better than its counterparts under other frameworks. Abundant experiments on public datasets show that our method is superior to the state-of-the-art methods in objective metrics, subjective visual effects and complexity. Our code will be made public.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑