Non-negative Sparse Modeling of Textures

Gabriel Peyré (1)

1 CEREMADE - CEntre de REcherches en MAthématiques de la DEcision

This paper presents a statistical model for textures that uses a non-negative decomposition on a set of local atoms learned from an exemplar. This model is described by the variances and kurtosis of the marginals of the decomposition of patches in the learned dictionary. A fast sampling algorithm allows to draw a typical image from this model. The resulting texture synthesis captures the geometric features of the original exemplar. To speed up synthesis and generate structures of various sizes, a multi-scale process is used. Applications to texture synthesis, image inpainting and texture segmentation are presented.

Mots clés: Texture syntesis; sparsity; dictionary learning

Domaines: Traitement du signal et de l'image [eess.SP]; Traitement du signal et de l'image [eess.SP]

Gabriel Peyré. Non-negative Sparse Modeling of Textures. SSVM'07, Jun 2007, Ischia, Italy. pp.628-639. ⟨hal-00365608⟩