Exemplar-based Inpainting: Technical Review and new Heuristics for better Geometric Reconstructions

International audienceThis paper proposes a technical review of exemplar-based inpainting approaches with a particular focus on greedy methods. Several comparative and illustrative experiments are provided to deeply explore and enlighten these methods, and to have a better understanding on the state-of-the-art improvements of these approaches. From this analysis three improvements over Criminisi et al. algorithm are then presented: 1) a tensor-based data term for a better selection of pixel candidates to fill in, 2) a fast patch lookup strategy to ensure a better global coherence of the reconstruction, and 3) a fast anisotropic spatial blending algorithm that reduces typical block artifacts using tensor models. Relevant comparisons to state-of-the-art inpainting methods are provided that exhibit the effectiveness of our contributions