High performance missing data detection and interpolation for video compression and restoration applications

In this paper, we explore the use of motion estimation methods to restore noisy motion pictures coming from degraded film within the framework of high-performance computing environments. Specifically, we investigate how the use of block-matching methods can outperform gradient-based methods (which are more sensible to little movements) also in the case of blotch detection in degraded film. Also, we show how a proposed method characterized by the use of a set of features together with multiresolution can be at the same time robust to noise and effective in motion compensated filtering, mainly concerning films that contain both large amounts of noise and fast/large motion objects in their frames. The peculiarities of the method are discussed and the model performance is assessed and compared with examples.