Dynamic Video Texture Inpainting Using Improving LDS
Mohsen Soryani *
School of Computer Engineering, Iran University of Science and Technology, Tehran, Iran.
Amanna Ghanbari
School of Computer Engineering, Iran University of Science and Technology, Tehran, Iran.
Abbas Koochari
School of Computer Engineering, Iran University of Science and Technology, Tehran, Iran.
*Author to whom correspondence should be addressed.
Abstract
Inpainting or completion is used with the aim of restoring damaged regions in images and video frames using the safe regions. This paper introduces a novel approach based on LDS (Linear Dynamic Systems) for inpainting of corrupted video frames which include dynamic textures. In this work, a mask is defined for each frame corresponding to the damaged portion of the frame; the mask determines the target region that will be completed by the proposed method. Notice that the mask is moving. To verify whether corrupted frames are reconstructed correctly or not, a measure named MS-SSIM (Multi-Scale Structural Similarity) is used. The value close to one for this scale introduces more similarity between the two components that are going to be compared. The obtained value for the above mentioned measure is very close to one for our results and the generated video is pleasant.
Keywords: Video inpainting, dynamic texture, LDS, MS-SSIM.