Ece Selin Böncü
An Application Of Inpainting-based Still Image Reanimation
single-input system that converts still paintings into short video sequences is developed. The system is composed of four separate blocks that are Digital Matting, Inpainting, Motion Modelling & Synthesis and Rendering Blocks. The input image is partitioned into object-background layers in Digital Matting Block. Inpainting Block is used to cover the holes in the background after object removal. Motion Modelling & Synthesis Block is responsible for creating an artificial motion field for the object layers and finally, in the Rendering Block, the layers are merged again to create the frames of the video. Within the scope of this thesis, the performance analysis of all are realized. Besides, a detailed analysis and experimentation is done on image inpainting techniques and their performance in the image-to-video converter system is discussed.
Prof. Dr. Gözde Bozdağı Akar