Back to articles
Volume: 28 | Article ID: art00012
Video inpainting of complex scenes based on local statistical model
  DOI :  10.2352/ISSN.2470-1173.2016.15.IPAS-193  Published OnlineFebruary 2016

This paper describes a framework for temporally consistent video completion. Proposed method allow to remove dynamic objects or restore missing or tainted regions present in a video sequence by utilizing spatial and temporal information from neighboring scenes. The algorithm iteratively performs following operations: achieve frame; update the scene model; update positions of moving objects; finding a set of descriptors that encapsulate the information necessary to reconstruct a frame; replace parts of the frame occupied by the objects marked for remove with use of a 3D patches. In this paper, we extend an image inpainting algorithm based texture and structure reconstruction by incorporating an improved strategy for video. Our algorithm is able to deal with a variety of challenging situations which naturally arise in video inpainting, such as the correct reconstruction of dynamic textures, multiple moving objects and moving background. Experimental comparisons to state-of-the-art video completion methods demonstrate the effectiveness of the proposed approach.

Subject Areas :
Views 13
Downloads 1
 articleview.views 13
 articleview.downloads 1
  Cite this article 

Voronin V.V, Sizyakin R.A, Marchuk V.I, Yigang Cen, Galustov G.G, Egiazarian K.O, "Video inpainting of complex scenes based on local statistical modelin Proc. IS&T Int’l. Symp. on Electronic Imaging: Image Processing: Algorithms and Systems XIV,  2016,

 Copy citation
  Copyright statement 
Copyright © Society for Imaging Science and Technology 2016
Electronic Imaging
Society for Imaging Science and Technology
7003 Kilworth Lane, Springfield, VA 22151 USA