A survey of exemplar-based texture synthesis

Lara Raad Cisa (1) , Axel Davy (2) , Agnès Desolneux (2, 3) , Jean-Michel Morel (2)

1 DITIC, universitat Pompeu Fabra
2 CMLA - Centre de Mathématiques et de Leurs Applications
3 CNRS - Centre National de la Recherche Scientifique

Exemplar-based texture synthesis is the process of generating, from an input sample, new texture images of arbitrary size and which are perceptually equivalent to the sample. The two main approaches are statistics-based methods and patch re-arrangement methods. In the first class, a texture is characterized by a statistical signature; then, a random sampling conditioned to this signature produces genuinely different texture images. The second class boils down to a clever ``copy-paste'' procedure, which stitches together large regions of the sample. Hybrid methods try to combines ideas from both approaches to avoid their hurdles. Current methods, including the recent CNN approaches, are able to produce impressive synthesis on various kinds of textures. Nevertheless, most real textures are organized at multiple scales, with global structures revealed at coarse scales and highly varying details at finer ones. Thus, when confronted with large natural images of textures the results of state-of-the-art methods degrade rapidly.

Mots clés: Texture Synthesis; Convolutional neural networks

Domaines: Traitement des images [eess.IV]; Réseau de neurones [cs.NE]; Analyse numérique [math.NA]

Lara Raad Cisa, Axel Davy, Agnès Desolneux, Jean-Michel Morel. A survey of exemplar-based texture synthesis. 2017. ⟨hal-01553841v2⟩