Texture Synthesis

1
Texture Synthesis

2
No Texture

• Using a sampling of 2D perlin Noise provides
  smooth hills.

3
Terrain Coloring

• Using a 1D texture map based on the altitude can
  provide many useful mapping.

4
Terrain Coloring

• Striped 1D texture map.

5
Terrain Coloring

• Using a 2D texture map provides richer detail,
  but is independent of the terrain.

6
Terrain Coloring

• More advanced coloring is based on altitude and
  slope.

7
Rolling Hills

• Flowers, trees, paths,

8
Procedural texture synthesis

• Gardner 85 sum a small number of sine waves of
  different periods and amplitudes.
• Perlin 85use band-limited noise function
• Turing 52 Reaction-diffusion system in
  developmental biology.
• Two or more chemicals can diffuse through an
  embryo and react with each other until a stable
  pattern of chemical concentration is reached.

9
Reaction-diffusion

• Texture buttons Andrew Witkin and Michael Kass

10
(No Transcript)
11
Texture synthesis on surfaces

• Retiling
• Sprinkle some new vertices onto the mesh
• Space them uniformly over the mesh using point
  repulsion.
• Remove old vertices and re-triangulate
• Create a hierarchy of meshes
• Neighborhood Construction
• flatten a set of nearby vertices
• resample the flattened patch

12
Point Repulsion
13
Point Repulsion
14
Mutual Tesselation
15
Neighborhood Construction
16
Neighborhood Construction
17
Texture Synthesis on meshes
18
Texture Synthesis on meshes
19
Texture Synthesis on meshes
20
2D Texture Synthesis
nxm Input Texture
NxM Output Texture

• The goal Synthesize an output texture which is
  perceptually similar to the input texture. Also
  ensure that the result contains sufficient
  variation.

21
Tiled Textures

• Take up little texture memory

22
Visual Comparison
Synthetic tilable texture
Simple tiling
Synthesized texture
23
Existing (and Impressive) Technology

• Pixel-Based
• Non-parametric Sampling Efros and Leung 1999
• Tree-structured Vector Quantization Wei and
  Levoy 2000
• Synthesizing Natural Textures Ashikhmin 2001
• Image Analogies Hertzmann et al. 2001
• Patch-Based
• Patch-Based Sampling Guo et al. 2001
• Image Quilting Efros and Freeman 2001
• Hierarchical Pattern Mapping Soler et al. 2002

24
Pixel-Based Texture Synthesis
Input
Output
Step n in Algorithm
25
Pixel-Based Texture Synthesis
Input
Output
Build L-shaped Neighborhood
26
Pixel-Based Texture Synthesis
Input
Output
Find Matching Neighborhood(s) in Input
27
Pixel-Based Texture Synthesis
Input
Output
Select Best Neighborhood from all Candidates
28
Pixel-Based Texture Synthesis
Input
Output
Copy Selected Pixel to Output
29
Pixel-Based Texture Synthesis
Input
Output
Repeat for all Pixels in this Row...
30
Pixel-Based Texture Synthesis
Input
Output
...and all other Output Rows
31
Patch-Based Texture Synthesis
Input
Output
Step n in Algorithm
32
Patch-Based Texture Synthesis
Input
Output
Patch to be Synthesized in this Step
33
Patch-Based Texture Synthesis
Input
Output
Build Neighborhood (Image Mask)
34
Patch-Based Texture Synthesis
Input
Output
Find Matching Neighborhood(s) in Input
35
Patch-Based Texture Synthesis
Input
Output
Select Best Neighborhood from all Candidates
36
Patch-Based Texture Synthesis
Input
Output
Copy Selected Patch to Output
37
Patch-Based Texture Synthesis
Input
Output
Apply some Overlap Repair Strategy ...
38
Patch-Based Texture Synthesis
Input
Output
... And we are done with this patch
39
Patch-Based Texture Synthesis
Input
Output
Repeat for all Patches in Output
40
Texture Synthesis

• Solid texture from 2D views
• Heeger Bergen 1995
• Ghazanfarpour Dischler 1999

2D Source
3D result
Images from HeegerBergen 1995
41
Previous Work

• Texture varying, morphing, and mixture
• Portilla Simoncelli 1999
• Bar-Joseph, El-Yaniv, Lichinski, Werman 2001
• Z. Liu, C. Liu, Shum, Yu 2003
• PVT paper in SIGGRAPH 2003

Source 1
Source 2
morphing
Image from PortillaSimoncelli 1999
42
Brodatz Results
aluminum wire
reptile skin
43
More Brodatz Results
french canvas
rafia weave
44
More Results
wood
granite
45
More Results
white bread
brick wall