A semi-global motion estimation of a repetition pattern region for frame interpolation
Nguyen Van Thang, Hyuk-Jae Lee · 2017
In motion compensated frame interpolation, a repetition pattern in an image makes it difficult to derive an accurate motion vector because multiple similar local minima exist in the search space of the matching cost for motion estimation. In order to improve the accuracy of motion estimation in a repetition region, this paper attempts a semi-global approach that exploits both local and global characteristics of a repetition region. Experimental results demonstrate that the proposed method significantly outperforms the previous local approach achieving the PSNR improvement by around 2.59 dB.