Abstract
The traditional approach in texture synthesis is to compare color neighborhoods with those of an exemplar. We show that quality is greatly improved if pointwise colors are replaced by appearance vectors that incorporate nonlocal information such as feature and radiance-transfer data. We perform dimensionality reduction on these vectors prior to synthesis, to create a new appearance-space exemplar. Unlike a texton space, our appearance space is low-dimensional and Euclidean. Synthesis in this information-rich space lets us reduce runtime neighborhood vectors from 5x5 grids to just 4 locations. Building on this unifying framework, we introduce novel techniques for coherent anisometric synthesis, surface texture synthesis directly in an ordinary atlas, and texture advection. Remarkably, we achieve all these functionalities in real-time, or 3 to 4 orders of magnitude faster than prior work.
Supplemental Material
- Ashikhmin, M. 2001. Synthesizing natural textures. Symposium on Interactive 3D Graphics, 217--226.]] Google ScholarDigital Library
- De Bonet, J. 1997. Multiresolution sampling procedure for analysis and synthesis of texture images. ACM SIGGRAPH, 361--368.]] Google ScholarDigital Library
- Efros, A., and Leung, T. 1999. Texture synthesis by non-parametric sampling. ICCV, 1033--1038.]] Google ScholarDigital Library
- Garber, D. 1981. Computational models for texture analysis and texture synthesis. PhD Dissertation, University of Southern California.]] Google ScholarDigital Library
- Heeger, D., and Bergen, J. 1995. Pyramid-based texture analysis/synthesis. ACM SIGGRAPH, 229--238.]] Google ScholarDigital Library
- Hertzmann, A., Jacobs, C., Oliver, N., Curless, B., and Salesin, D. 2001. Image analogies. ACM SIGGRAPH, 327--340.]] Google ScholarDigital Library
- Hertzmann, A., and Zorin, D. 2000. Illustrating smooth surfaces. ACM SIGGRAPH, 517--526.]] Google ScholarDigital Library
- Kwatra, V., Essa, I., Bobick, A., and Kwatra, N. 2005. Texture optimization for example-based synthesis. SIGGRAPH, 795--802.]] Google ScholarDigital Library
- Lefebvre, S., and Hoppe, H. 2005. Parallel controllable texture synthesis. ACM SIGGRAPH, 777--786.]] Google ScholarDigital Library
- Leung, T., and Malik, J. 2001. Representing and recognizing the visual appearance of materials using 3D textons. IJCV 43(1), 29--44.]] Google ScholarDigital Library
- Liang, L., Liu, C., Xu, Y., Guo, B., and Shum, H.-Y. 2001. Real-time texture synthesis by patch-based sampling. ACM TOG 20(3), 127--150.]] Google ScholarDigital Library
- Magda, S., and Kriegman, D. 2003. Fast texture synthesis on arbitrary meshes. Eurographics Symposium on Rendering, 82--89.]] Google ScholarDigital Library
- Malik, J., Belongie, S., Shi, J., and Leung, T. 1999. Textons, contours and regions: Cue integration in image segmentation. ICCV, 918--925.]] Google ScholarDigital Library
- Neyret, F., and Cani, M.-P. 1999. Pattern-based texturing revisited. ACM SIGGRAPH, 235--242.]] Google ScholarDigital Library
- Neyret, F. 2003. Advected textures. Symposium on computer animation, 147--153.]] Google ScholarDigital Library
- Popat, K., and Picard, R. 1993. Novel cluster-based probability model for texture synthesis, classification, and compression. Visual Communications and Image Processing, 756--768.]]Google Scholar
- Portilla, J., and Simoncelli, E. 2000. A parametric texture model based on joint statistics of complex wavelet coefficients. IJCV (40) 1.]] Google ScholarDigital Library
- Praun, E., Finkelstein, A., and Hoppe, H. 2000. Lapped textures. ACM SIGGRAPH, 465--470.]] Google ScholarDigital Library
- Roweis, S. 1997. EM algorithms for PCA and SPCA. NIPS, 626--632.]] Google ScholarDigital Library
- Roweis, S., and Saul, L. 2000. Nonlinear dimensionality reduction by locally linear embedding. Science, 290:2323--2326.]]Google ScholarCross Ref
- Sloan, P.-P., Liu, X., Shum, H.-Y., and Snyder, J. 2003. Bi-scale radiance transfer. ACM SIGGRAPH, 370--375.]] Google ScholarDigital Library
- Taponecco, F., and Alexa, M. 2004. Steerable texture synthesis. Eurographics Conference.]]Google Scholar
- Tenenbaum, J., De Silva, V., and Langford, J. 2000. A global geometric framework for nonlinear dimensionality reduction. Science, 290:2319--2323.]]Google ScholarCross Ref
- Tong, X., Zhang, J., Liu, L., Wang, X., Guo, B., and Shum, H.-Y. 2002. Synthesis of bidirectional texture functions on arbitrary surfaces. ACM SIGGRAPH, 665--672.]] Google ScholarDigital Library
- Turk, G. 2001. Texture synthesis on surfaces. SIGGRAPH, 347--354.]] Google ScholarDigital Library
- Wei, L.-Y., and Levoy, M. 2000. Fast texture synthesis using tree-structured vector quantization. ACM SIGGRAPH, 479--488.]] Google ScholarDigital Library
- Wei, L.-Y., and Levoy, M. 2001. Texture synthesis over arbitrary manifold surfaces. ACM SIGGRAPH, 355--360.]] Google ScholarDigital Library
- Wei, L.-Y., and Levoy, M. 2003. Order-independent texture synthesis. http://graphics.stanford.edu/papers/texture-synthesis-sig03/.]]Google Scholar
- Wu, Q., and Yu, Y. 2004. Feature matching and deformation for texture synthesis. ACM SIGGRAPH, 362--365.]] Google ScholarDigital Library
- Ying, L., Hertzmann, A., Biermann, H., and Zorin, D. 2001. Texture and shape synthesis on surfaces. Symposium on Rendering, 301--312.]] Google ScholarDigital Library
- Zhang, J., Zhou, K., Velho, L., Guo, B., and Shum, H.-Y. 2003. Synthesis of progressively-variant textures on arbitrary surfaces. ACM SIGGRAPH, 295--302.]] Google ScholarDigital Library
Index Terms
- Appearance-space texture synthesis
Recommendations
Appearance-space texture synthesis
SIGGRAPH '06: ACM SIGGRAPH 2006 PapersThe traditional approach in texture synthesis is to compare color neighborhoods with those of an exemplar. We show that quality is greatly improved if pointwise colors are replaced by appearance vectors that incorporate nonlocal information such as ...
Texture Synthesis Using the Structure Tensor
This paper proposes a two-stage texture synthesis algorithm. At the first stage, a structure tensor map carrying information about the local orientation is synthesized from the exemplar's data and used at the second stage to constrain the synthesis of the ...
Texture Synthesis with Grouplets
This paper proposes a new method to synthesize and inpaint geometric textures. The texture model is composed of a geometric layer that drives the computation of a new grouplet transform. The geometry is an orientation flow that follows the patterns of ...
Comments