Rethinking Deinterlacing for Early Interlaced Videos
Rethinking Deinterlacing for Early Interlaced Videos
复制标题
DOI：
10.1109/tcsvt.2021.3112548
复制
发表时间：
2020-11
影响因子：
8.4
通讯作者：
Yang Zhao;Wei Jia;Ronggang Wang
中科院分区：
文献类型：
--
作者：
Yang Zhao;Wei Jia;Ronggang Wang
近年来，早期视频的高清还原备受关注。现实世界的隔行扫描视频通常包含各种退化与隔行扫描伪影混合，如噪声和压缩伪影。然而，传统的去隔行方法只关注隔行扫描的逆过程，无法去除这些复杂的伪影。因此，本文提出了一种图像去隔行网络（DIN），这是专门设计的联合消除交织与其他文物。DIN由两个阶段组成，即，用于分割和充分使用相邻场的信息的协作垂直内插阶段，以及用于感知运动和抑制重影伪影的场合并阶段。实验结果表明，所提出的DIN在合成和真实世界的测试集上的有效性。
In recent years, high-definition restoration of early videos have received much attention. Real-world interlaced videos usually contain various degradations mixed with interlacing artifacts, such as noises and compression artifacts. Unfortunately, traditional deinterlacing methods only focus on the inverse process of interlacing scanning, and cannot remove these complex and complicated artifacts. Hence, this paper proposes an image deinterlacing network (DIN), which is specifically designed for joint removal of interlacing mixed with other artifacts. The DIN is composed of two stages, i.e., a cooperative vertical interpolation stage for splitting and fully using the information of adjacent fields, and a field-merging stage to perceive movements and suppress ghost artifacts. Experimental results demonstrate the effectiveness of the proposed DIN on both synthetic and real-world test sets.