Non-negative Sparse Modeling of Textures

Peyré, Gabriel

Peyré, Gabriel (2007), Non-negative Sparse Modeling of Textures, in Sgallari, Fiorella; Paragios, Nikos; Murli, Almerico, Scale Space and Variational Methods in Computer Vision First International Conference, SSVM 2007, Ischia, Italy, May 30 - June 2, 2007, Proceedings, Springer, p. 628-639

Type

Communication / Conférence

External document link

http://hal.archives-ouvertes.fr/hal-00365608/en/

Date

2007

Conference title

Scale Space and Variational Methods in Computer Vision (SSVM'07)

Conference date

2007-05

Conference city

Ischia

Conference country

Italie

Book title

Scale Space and Variational Methods in Computer Vision First International Conference, SSVM 2007, Ischia, Italy, May 30 - June 2, 2007, Proceedings

Book author

Sgallari, Fiorella; Paragios, Nikos; Murli, Almerico

Publisher

Springer

Series title

Lecture Notes in Computer Science

Series number

4485

ISBN

978-3-540-72822-1

Number of pages

931

Pages

628-639

Abstract (EN)

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.

Subjects / Keywords

Texture syntesis; sparsity; dictionary learning