1 / 31

Texture Synthesis over Arbitrary Manifold Surfaces

Texture Synthesis over Arbitrary Manifold Surfaces. Li-Yi Wei Marc Levoy. Computer Graphics Group Stanford University. Introduction. Synthesize a surface texture by coloring mesh vertices. +. Input Texture. Input Mesh. Result. Desirable Properties.

winbush
Télécharger la présentation

Texture Synthesis over Arbitrary Manifold Surfaces

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

  1. Texture Synthesis overArbitrary Manifold Surfaces Li-Yi Wei Marc Levoy Computer Graphics Group Stanford University

  2. Introduction Synthesize a surface texture by coloring mesh vertices + Input Texture Input Mesh Result

  3. Desirable Properties • Share advantages of 2D algorithm [SIGGRAPH 2000] • Quality • Efficient • General • Easy to use • Minimum distortion • Minimum discontinuity

  4. Previous Work • Texture Mapping • Global [Catmull’74, Bier’86, Levy’98] • Local • Triangle tiles [Neyret’99] • Lapped textures [Praun’00]

  5. Previous Work • 3D Texture synthesis • procedural [Perlin’85, Turk’91, Witkin’91] • from example • surface texture [Gagalowicz’86, Turk’01, Ying’01] • volume texture [Heeger’95, Ghazanfarpour ’96]

  6. Previous Work • 2D Texture from Example • pyramid matching [Heeger’95, Simoncelli’98] • block shuffling [De Bonet’97, Xu’00] • Markov Random Field [Popat’93] • neighborhood search [Efros’99, Wei’00]

  7. Copy Search noise Input pyramid Output pyramid Texture Synthesis byNeighborhood Search noise

  8. Search Surface Texture Synthesis byNeighborhood Search Input pyramid Output pyramid

  9. mesh v normal u ? ? tangent bitangent Differences betweenImages and Meshes image Our Solution mesh re-tiling [Turk’92] grid ? Pixels/Vertices user-specified relaxation random Local Orientation (Vector field) Synthesis Order scanline random ? flattening/resampling Neighborhood

  10. Process 1. Build image/mesh pyramids 2. Assign texture orientation 3. Generate texture

  11. Image & Mesh Pyramids Mesh Retiling [Turk’92]

  12. Retiling Density 24576 vertices 73728 vertices

  13. Texture Orientation • Methods for orienting textures • user-specified • random (for isotropic textures) • smooth or symmetric (for anisotropic textures) • by relaxation

  14. 4-way symmetric texture 4-way symmetric vector field Texture Orientation

  15. Texture Orientation by Relaxation • Minimize an error function • similar to [Hertzmann’00, Pedersen’95]

  16. Synthesis

  17. Synthesis : 2 Lowest Levels

  18. Random copy Synthesis : Lowest Level

  19. Copy Shooting normal Search Synthesis Pass1 : Extrapolation

  20. Copy Search Synthesis Pass2 :Full Neighborhood

  21. Neighborhood Comparison compare ?

  22. Resampled Grid Compare Resample Flatten (Maillot’93) 2D Patch Mesh Neighborhood 3D Patch

  23. Accelerating Neighborhood Search • Tree-structured Vector Quantization [Wei’00]

  24. Multiresolution Synthesis

  25. Results:Random Orientation

  26. Results:Other Orientations Random User-specified Relaxation 2-way symmetry 4-way symmetry

  27. Results smooth 4-way symmetry random

  28. Results Surface displacement smooth 2-way symmetry 2-way symmetry

  29. Summary of Differences Turk’s approach Our approach Vector field smooth random, symmetric Traversal order sweeping random Neighborhood surface marching flattening/resampling Mesh hierarchy explicit parent/child shooting normal

  30. Future Work • Texture transfer between models • Texturing animated models • Mesh signal processing

  31. More Information http://graphics.stanford.edu/projects/texture/

More Related