Two-Stage volumetric texture synthesis based on structural information

Volumetric texture synthesis is mainly used in computer graphics for texturing objects in order to increase the realism of the 3D scenario. It is also of particular interest in many application domains such as studying the three-dimensional internal structure of materials and modelling volumetric data obtained by 3D imaging techniques for medical purposes. Based on a previously proposed 2D structure/texture synthesis algorithm, this paper proposes a two-stage 3D texture synthesis approach where the volumetric structure layer of the input texture is first synthesized, then used to help the synthesis of the volumetric texture. Results show that, using the structural information helps the synthesis of the volumetric texture and can outperform the synthesis based only on intensity information.

[1]  Eero P. Simoncelli,et al.  A Parametric Texture Model Based on Joint Statistics of Complex Wavelet Coefficients , 2000, International Journal of Computer Vision.

[2]  Li-Yi Wei,et al.  Texture synthesis from multiple sources , 2003, SIGGRAPH '03.

[3]  Adib Akl,et al.  Texture Synthesis Using the Structure Tensor , 2015, IEEE Transactions on Image Processing.

[4]  Jean-Pierre Da Costa,et al.  Non-parametric synthesis of laminar volumetric textures from a 2D sample , 2012, BMVC.

[5]  Rupert Paget,et al.  Texture synthesis via a noncausal nonparametric multiscale Markov random field , 1998, IEEE Trans. Image Process..

[6]  J. Bigun,et al.  Optimal Orientation Detection of Linear Symmetry , 1987, ICCV 1987.

[7]  Jean-Pierre Da Costa,et al.  Maximum-Likelihood Based Synthesis of Volumetric Textures From a 2D Sample , 2014, IEEE Transactions on Image Processing.

[8]  Jean-Pierre Da Costa,et al.  An image-guided atomistic reconstruction of pyrolytic carbons , 2009 .

[9]  Marc Levoy,et al.  Fast texture synthesis using tree-structured vector quantization , 2000, SIGGRAPH.

[10]  Laurent Jacques,et al.  A panorama on multiscale geometric representations, intertwining spatial, directional and frequency selectivity , 2011, Signal Process..

[11]  Jeremy R. Cooperstock,et al.  An Improved Representation of Junctions Through Asymmetric Tensor Diffusion , 2006, ISVC.

[12]  Christian Germain,et al.  Synthesis of solid textures based on a 2D example: application to the synthesis of 3D carbon structures observed by transmission electronic microscopy , 2010, Electronic Imaging.

[13]  Gabriel Peyré,et al.  Texture Synthesis with Grouplets , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[14]  Adib Akl,et al.  Structure tensor based synthesis of directional textures for virtual material design , 2014, 2014 IEEE International Conference on Image Processing (ICIP).

[15]  J.-P. Da Costa,et al.  Nanoscale structure and texture of highly anisotropic pyrocarbons revisited with transmission electron microscopy, image processing, neutron diffraction and atomistic modeling , 2014 .

[16]  Dani Lischinski,et al.  Solid texture synthesis from 2D exemplars , 2007, ACM Trans. Graph..

[17]  Alexei A. Efros,et al.  Image quilting for texture synthesis and transfer , 2001, SIGGRAPH.

[18]  Songde Ma,et al.  Model driven synthesis of natural textures for 3-D scenes , 1986, Comput. Graph..

[19]  Adib Akl,et al.  Two-stage Color Texture Synthesis using the Structure Tensor Field , 2015, GRAPP.

[20]  Nicholas Ayache,et al.  A Riemannian Framework for the Processing of Tensor-Valued Images , 2005, DSSCV.