Video frame interpolation using 3-D total variation regularized completion

A new video frame interpolation technique is proposed in this paper.We first use the classical motion compensation interpolation (MCI), but only for motion vectors (MVs) marked as reliable in our classification procedure. To fill in the regions where no such MV is available, we proposed a novel 3-D total variation regularized completion model, which exploits both temporal and spatial smoothness among video frames. Experiments demonstrate its superior performance compared to several classical methods, both in visual quality and PSNR values, while the typical artifacts are significantly reduced.