Download presentation
Presentation is loading. Please wait.
Published byKaylie Bagnell Modified over 9 years ago
2
Texture Synthesis on [Arbitrary Manifold] Surfaces Presented by: Sam Z. Glassenberg* * Several slides borrowed from Wei/Levoy presentation
3
Topics Investigated Thus Far 2D Texture Mapping (CS318) 3D Textures (Hypertexture) 2D Texture Synthesis
4
+ Synthesize a texture on a surface by coloring mesh vertices Input TextureInput MeshResult Today’s Goal
5
Vertex Painting Advantages –Speed No additional transformation required –Simplicity –Uniformly distributed across geometry Disadvantages –Texture resolution dependent on mesh complexity
6
2 SIGGRAPH Papers: 1.Texture Synthesis on Surfaces, by Greg TurkTexture Synthesis on Surfaces 2.Texture Synthesis over Arbitrary Manifold Surfaces, by Li-Yi Wei and Marc LevoyTexture Synthesis over Arbitrary Manifold Surfaces
8
Desirable Properties Share advantages of 2D algorithm –Quality –Efficient –General –Easy to use Minimum distortion Minimum discontinuity
9
Differences between Images and Meshes image mesh Synthesis Order Pixels/Vertices Local Orientation (Vector field) ? ? scanline u v grid Neighborhood normal ? ? tangent bitangent
10
Wei/Levoy Solution image mesh Synthesis Order Pixels/Vertices Local Orientation (Vector field) ? ? scanline u v grid Neighborhood normal ? ? tangent bitangent Wei and Levoy mesh re-tiling [Turk’92] user-specified relaxation random flattening/resampling
11
Turk Solution Turk repulsion [Turk’91] User specified/ interpolated sweeping Surface marching image mesh Synthesis Order Pixels/Vertices Local Orientation (Vector field) ? ? scanline u v grid Neighborhood normal ? ? tangent bitangent
12
Both Papers Extend Fast Texture Synthesis using Tree-structured Vector Quantization Specifically by generalizing their definition of “search neighborhoods” to apply to meshes
13
Texture Synthesis by Neighborhood Search noise Input pyramid noise Output pyramid Search Copy
14
Surface Texture Synthesis by Neighborhood Search (Wei/Levoy) Input pyramid Output pyramid Search
15
Process 1. Build image/mesh pyramids 2. Assign texture orientation/Computation order 3. Generate texture
16
What aspects of image pyramids must we maintain in mesh pyramids? Uniform density Power-of-two complexity differences between levels
17
Image & Mesh Pyramids Mesh Retiling [Turk’92]
18
2 Turk-ish Methods for Mesh Retiling Turk ’92, used by Wei/Levoy –Uniformly distributes mesh vertices –Requires “shooting normals” to move between levels Turk ’91, used by Turk –Uniformly distributes mesh vertices –Maintains parent/child relationship between levels
19
Retiling Density 24576 vertices73728 vertices
20
Turk ‘91 Create a mesh hierarchy in which mesh M k = (V k, T k ) is defined by its Vertices and Triangles –For the lowest mesh in the hierarchy, place n points on the surface –Use repulsion to distribute points easily –Add 3n points to make the next level –Repeat Connect points by projecting nearby points onto a tangent plane Perform Delaunay triangulation to reduce triangles
21
Now, we need to determine orientation… In Turk’s method, we use this orientation to determine the computation order (Surface Sweeping) In Wei/Levoy’s method, orientation is needed to “flatten” the neighborhoods.
22
Texture Orientation Generate a coordinate frame Three orthogonal axes – s (texture right) – t (texture up) – n (surface normal)
23
Texture Orientation Methods for orienting textures –user-specified (Turk) –random (Wei/Levoy) –smooth or symmetric (Wei/Levoy)
24
Texture Orientation (User-specified)
25
4-way symmetric texture 4-way symmetric vector field Texture Orientation (Symmetry)
26
Texture Orientation random2-way symmetry4-way symmetry
27
Texture Orientation (Relaxation) Minimize an error function
28
Results (Wei/Levoy): Random Orientation
29
Results (Wei/Levoy): Other Orientations RandomUser-specified Relaxation 2-way symmetry 4-way symmetry
30
Texture Synthesis on Surfaces: Wei/Levoy Style
31
Synthesis
32
Synthesis : 2 Lowest Levels
33
Synthesis : Lowest Level Random copy
34
Synthesis Pass1 : Extrapolation Search Copy Shooting normal
35
Mesh Neighborhood Resample Compare Resampled Grid 2D Patch 3D Patch Flatten (Maillot’93)
36
Neighborhood Flattening Project the triangles adjacent to p onto p’s local texture coordinate system Add triangles one-at-a-time until neighborhood template is covered
37
Neighborhood Comparison compare ?
38
Synthesis Pass 2 : Full Neighborhood Search Copy
39
Multiresolution Synthesis
40
Texture Synthesis on Surfaces: According to Turk
41
Turk’s Surface Sweeping Select an anchor vertex A Assign s(v) = sweep distance to vertex v along the vector field from A (for all v) Consensus orientation b/w 2 vertices v and w: O vw = (O(v) + O(w))/2 Calculate a new s(v) as a weighted average that its neighboring values dictate it should have. Visit vertices in order by sweep distance
42
Turk’s Texture Synthesis (Pseudocode) I = Input texture N(v) = Neighborhood around v M(a,b) = Neighborhood around (a,b) D(M,N) = Match Value (sum of squared differences)
43
Turk’s Mesh Neighborhoods r = average distance between mesh vertices O(v) = Surface tangent vector P(v) = O(v) rotated 90 o about surface normal Together, O and P make a coordinate frame ! u v normal P O Now, we can traverse the surface by point repelling
44
Point Repelling Use color interpolation to determine color at current surface point Move r in the direction of O or P When an edge is reached, fold the path over the next polygon
45
Results smooth4-way symmetryrandom
46
Results Surface displacement smooth2-way symmetry
47
Results
48
Summary of Differences Turk’s approachOur approach Vector field Traversal order Neighborhood Mesh hierarchy smoothrandom, symmetric sweepingrandom surface marchingflattening/resampling explicit parent/childshooting normal
Similar presentations
© 2024 SlidePlayer.com Inc.
All rights reserved.