Image inpainting with adaptive linear predictor

Jing Liu, Guangtao Zhai, Xiaokang Yang, Chang Wen Chen

Abstract: In this paper, a novel examplar-based inpainting algorithm with adaptive linear predictor is proposed. The patches in the damaged region are sequentially estimated with a linear combination of several nearest neighboring patches. The number of candidate patch is automatically tuned to local contexts based on Bayesian Information Criterion (BIC). The flexibility of the order-adaptive predictor makes the proposed algorithm suitable for both structural regions and detailed textures. The multi-scale framework and a novel propagation order are also involved to further improve the inpainting performance. Compared to the state-of-the-art image inpainting algorithms, experimental results show that the proposed method gives comparative or better performance.