Chaos Mosaic: Fast and Memory Efficient Texture Synthesis

We present a procedural method for synthesizing large textures from an input texture sample. The basis of our algorithm is the chaos mosaic, a technique for synthesizing textures with an even and visually stochastic distribution of the local features of the input sample. The chaos mosaic is fast. For synthesizing textures of the same size and comparable quality, our algorithm is orders of magnitude faster than existing algorithms. On a PC we can synthesize a 512 512 texture from a 64 64 sample in just 0.03 second. More importantly, the chaos mosaic facilitates memory efficient texture rendering through procedural texturing. Like traditional solid texture techniques, the chaos mosaic allows us to synthesize and render synthetic textures that, if stored explicitly as textures, would require prohibitively large amount of storage. As an example, we demonstrate that an 100k 100k synthetic texture can be interactively visualized on a modest PC without suffering from latency. Finally, the chaos mosaic can drastically reduce the bandwidth for interactive 3D graphics delivered across the internet.

[1]  V. I. Arnolʹd,et al.  Ergodic problems of classical mechanics , 1968 .

[2]  D. Haar,et al.  Foundations of classical and quantum statistical mechanics , 1969 .

[3]  Edwin Earl Catmull,et al.  A subdivision algorithm for computer display of curved surfaces. , 1974 .

[4]  Donald S. Fussell,et al.  Computer rendering of stochastic models , 1982, Commun. ACM.

[5]  H. Schuster Deterministic chaos: An introduction , 1984 .

[6]  Darwyn R. Peachey,et al.  Solid texturing of complex surfaces , 1985, SIGGRAPH.

[7]  Robert L. Cook,et al.  The Reyes image rendering architecture , 1987, SIGGRAPH.

[8]  Ken Perlin,et al.  An image synthesizer , 1988 .

[9]  J. P. Lewis,et al.  Algorithms for solid noise synthesis , 1989, SIGGRAPH.

[10]  Yan Gu Evidences of classical and quantum chaos in the time evolution of nonequilibrium ensembles , 1990 .

[11]  Pat Hanrahan,et al.  A language for shading and lighting calculations , 1990, SIGGRAPH.

[12]  Andrew Witkin,et al.  Reaction-diffusion textures , 1991, SIGGRAPH.

[13]  Greg Turk,et al.  Generating textures on arbitrary surfaces using reaction-diffusion , 1991, SIGGRAPH.

[14]  James R. Bergen,et al.  Pyramid-based texture analysis/synthesis , 1995, Proceedings., International Conference on Image Processing.

[15]  Jay Torborg,et al.  Talisman: commodity realtime 3D graphics for the PC , 1996, SIGGRAPH.

[16]  Maneesh Agrawala,et al.  Rendering from compressed textures , 1996, SIGGRAPH.

[17]  Pat Hanrahan,et al.  Rendering complex scenes with memory-coherent ray tracing , 1997, SIGGRAPH.

[18]  Jeremy S. De Bonet,et al.  Multiresolution sampling procedure for analysis and synthesis of texture images , 1997, SIGGRAPH.

[19]  Michael Shantz,et al.  Multi-level texture caching for 3D graphics hardware , 1998, Proceedings. 25th Annual International Symposium on Computer Architecture (Cat. No.98CB36235).

[20]  Alexei A. Efros,et al.  Texture synthesis by non-parametric sampling , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[21]  Eero P. Simoncelli,et al.  Texture modeling and synthesis using joint statistics of complex wavelet coefficients , 1999 .

[22]  Song-Chun Zhu,et al.  Exploring Texture Ensembles by Efficient Markov Chain Monte Carlo-Toward a 'Trichromacy' Theory of Texture , 2000, IEEE Trans. Pattern Anal. Mach. Intell..