Skip to Main content Skip to Navigation
Journal articles

Variational Texture Synthesis with Sparsity and Spectrum Constraints

Abstract : This paper introduces a new approach for texture synthesis. We propose a unified framework that both imposes first order statistical constraints on the use of atoms from an adaptive dictionary, as well as second order constraints on pixel values. This is achieved thanks to a variational approach, the minimization of which yields local extrema, each one being a possible texture synthesis. On the one hand, the adaptive dictionary is created using a sparse image representation rationale, and a global constraint is imposed on the maximal number of use of each atom from this dictionary. On the other hand, a constraint on second order pixel statistics is achieved through the power spectrum of images. An advantage of the proposed method is its ability to truly synthesize textures, without verbatim copy of small pieces from the exemplar. In an extensive experimental section, we show that the resulting synthesis achieves state of the art results, both for structured and small scale textures.
Document type :
Journal articles
Complete list of metadatas

Cited literature [39 references]  Display  Hide  Download
Contributor : Guillaume Tartavel <>
Submitted on : Thursday, November 6, 2014 - 2:54:04 PM
Last modification on : Wednesday, June 24, 2020 - 4:18:59 PM




Guillaume Tartavel, Yann Gousseau, Gabriel Peyré. Variational Texture Synthesis with Sparsity and Spectrum Constraints. Journal of Mathematical Imaging and Vision, Springer Verlag, 2015, 52 (1), pp.124-144. ⟨10.1007/s10851-014-0547-7⟩. ⟨hal-00881847v3⟩



Record views


Files downloads