Twist tensor total variation regularized-reweighted nuclear norm based tensor completion for video missing area recovery

This paper focuses on recovering multi-dimensional signal called tensor which is corrupted by random missing areas. The performance of the conventional tensor completion techniques deteriorate when the tensor multi-rank is large and/or large missing areas. Moreover, these techniques are weak in preserving the edges in the signals like images/videos. This paper proposes an efficient method to overcome these problems by simultaneously combining novel twist tensor total variation norm to exploit spatio-temporal correlation and tensor-Singular Value Decomposition (t-SVD) based reweighted nuclear norm to improve low multi-rank tensor recovery. The twist tensor total variation norm takes care of edges in the recovered data and aids the recovery of missing areas by utilising the similarities in the adjacent samples. The reweighted nuclear norm handles corrupted large rank tensors by sparsity enhancement via reweighting its singular values. The effectiveness of the proposed method is established by applying to video completion problem, and experimental results reveal that the algorithm outperforms its counterparts.