Optical Flow Guided TV-L Video Interpolation and Restoration

The ability to generate intermediate frames between two given images in a video sequence is an essential task for video restoration and video post-processing. In addition, restoration requires robust denoising algorithms, must handle corrupted frames and recover from impaired frames accordingly. In this paper we present a unified framework for all these tasks. In our approach we use a variant of the TV-L denoising algorithm that operates on image sequences in a space-time volume. The temporal derivative is modified to take the pixels’ movement into account. In order to steer the temporal gradient in the desired direction we utilize optical flow to estimate the velocity vectors between consecutive frames. We demonstrate our approach on impaired movie sequences as well as on benchmark datasets where the ground-truth is known.