Microtexture Inpainting through Gaussian Conditional Simulation

Bruno Galerne (1) , Arthur Leclaire (2) , Lionel Moisan (1)

1 MAP5 - UMR 8145 - Mathématiques Appliquées Paris 5
2 CMLA - Centre de Mathématiques et de Leurs Applications

Image inpainting consists in filling missing regions of an image by inferring from the surrounding content. In the case of texture images, inpainting can be formulated in terms of conditional simulation of a stochastic texture model. Many texture synthesis methods thus have been adapted to texture inpainting, but these methods do not offer theoretical guarantees since the conditional sampling is in general only approximate. Here we show that in the case of Gaussian textures, inpainting can be addressed with perfect conditional simulation relying on kriging estimation. We thus obtain a micro-texture inpainting algorithm that is able to fill holes of any shape and size in an efficient manner while respecting exactly a stochastic model.

Keywords: Gaussian texture; texture synthesis; Inpainting; conditional simulation; kriging

Domains: Image Processing [eess.IV]

Bruno Galerne, Arthur Leclaire, Lionel Moisan. Microtexture Inpainting through Gaussian Conditional Simulation. IEEE International Conference on Acoustics, Speech, and Signal Processing, Mar 2016, Shanghai, China. ⟨10.1109/ICASSP.2016.7471867⟩. ⟨hal-01214695v3⟩