Microtexture Inpainting through Gaussian Conditional Simulation

Abstract : 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.
Document type :
Conference papers
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01214695
Contributor : Lionel Moisan <>
Submitted on : Thursday, February 18, 2016 - 5:00:25 PM
Last modification on : Thursday, April 11, 2019 - 4:02:09 PM

File

2015-32r.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01214695, version 2

Citation

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. ⟨hal-01214695v2⟩

Share

Metrics

Record views

81

Files downloads

36