Video Inpainting Algorithm Using Spatio-Temporal Consistency

A new video inpainting algorithm is proposed for removing unwanted or erroneous objects from video data. The proposed algorithm fills a mask region with source blocks from unmasked areas, while keeping spatio-temporal consistency. First, a 3-dimensional graph is constructed over consecutive frames. It defines a structure of nodes over which the source blocks are pasted. Then, we form temporal block bundles using the motion information. The best block bundles, which minimize an objective function, are arranged in the 3-dimensional graph. Extensive simulation results demonstrate that the proposed algorithm can yield visually pleasing video inpainting results even for dynamic sequences.