Static object removal from video scene using local similarity

Video completion is an active subject in video processing, which deals with the recovery of the damaged data. Reconstruction of damaged parts after object removal of digital video is an important trend in artwork restoration. Most previous video inpainting and completion approaches consume more time in extensive search to find the best patch to restore the damaged area. In addition to that, visual artifacts appear when the damaged area is large. In this paper, we present a fast and efficient video completion method to recover static damaged area without the extensive search process. The proposed method is based on frame local similarity and 3D hole filling. The proposed method maintains the spatial and temporal consistency. Moreover it reduces the completion time to few milliseconds.