This paper presents a game-theoretical approach to provide a framework for optimal template selection in image prediction. Image prediction is an effective tool for coding still images and intra pictures in videos. Template matching algorithms which use neighboring blocks of the prediction target as templates have been widely used for image prediction. The assumption of these approaches is that the template has similar textural structures as the prediction target. Up to now these approaches all use pre-fixed templates for all prediction targets. However, in real images, these fixed templates are very likely to contain textures that are not or are not significant in the prediction targets and these insignificant textures introduce larger prediction residues. In this paper, we propose a coalitional game in which every pixel is treated as a player and tries to seek partners to form a coalition to capture the textural structure. By forming a coalition, every player in the coalition can obtain a gain of improving the ability of capturing the textural structure of coalition while incurring a cost of introducing textural variance within the coalition. Experimental results show that the proposed game-theoretical approach outperforms the conventional pre-fixed template matching prediction up to 2dB coding gain.
展开▼
