Non-negative Sparse Modeling of Textures - Archive ouverte HAL Access content directly
Conference Papers Year : 2007

Non-negative Sparse Modeling of Textures


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.
Fichier principal
Vignette du fichier
PeyreSSVM07-Spars.pdf (1.48 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-00365608 , version 1 (03-03-2009)


  • HAL Id : hal-00365608 , version 1


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


Gmail Facebook X LinkedIn More