Video Completion as Noise Removal

AbstractVideo completion algorithms have concentrated on obtaining visually consistent solutions to ll-in the missing portions, without any emphasis on the physical correctness of the video. Resulting solutions thus use texture or image structure based cues and are limited in the situations they can handle. In this paper we take a model based signal processing approach to video completion [1]. Completion of the video is then dened as satisfying the given model by detecting and removing the error (selected parts of the video to be replaced). Given a probabilistic model, video completion then becomes an unsupervised learning algorithm with the input video giving a noisy version. Dense completion is the automatic inferencing of the noise-less or true video from the input. This approach nds a solution that satises visual coherence and is applicable to a wide variety of scenarios. We demonstrate the efcacy of our approach and its wide applicability using two scenarios. I