Advanced Computer Graphics (Fall 2010) CS 283, Lecture 26 Texture Synthesis Ravi Ramamoorthi...
-
Upload
dwayne-barker -
Category
Documents
-
view
219 -
download
0
Transcript of Advanced Computer Graphics (Fall 2010) CS 283, Lecture 26 Texture Synthesis Ravi Ramamoorthi...
![Page 1: Advanced Computer Graphics (Fall 2010) CS 283, Lecture 26 Texture Synthesis Ravi Ramamoorthi cs283/fa10 Slides, lecture.](https://reader035.fdocuments.in/reader035/viewer/2022062803/56649f285503460f94c4042a/html5/thumbnails/1.jpg)
Advanced Computer Graphics Advanced Computer Graphics (Fall 2010)(Fall 2010)
CS 283, Lecture 26
Texture Synthesis
Ravi Ramamoorthihttp://inst.eecs.berkeley.edu/~cs283/fa10
Slides, lecture courtesy Alexei Efros, from CMU lecture
![Page 2: Advanced Computer Graphics (Fall 2010) CS 283, Lecture 26 Texture Synthesis Ravi Ramamoorthi cs283/fa10 Slides, lecture.](https://reader035.fdocuments.in/reader035/viewer/2022062803/56649f285503460f94c4042a/html5/thumbnails/2.jpg)
Weather Forecast for Dummies Weather Forecast for Dummies
Let’s predict weather: Given today’s weather only, we want to know tomorrow’s Suppose weather can only be {Sunny, Cloudy, Raining}
The “Weather Channel” algorithm: Over a long period of time, record:
How often S followed by R How often S followed by S Etc.
Compute percentages for each state: P(R|S), P(S|S), etc.
Predict the state with highest probability! It’s a Markov Chain
![Page 3: Advanced Computer Graphics (Fall 2010) CS 283, Lecture 26 Texture Synthesis Ravi Ramamoorthi cs283/fa10 Slides, lecture.](https://reader035.fdocuments.in/reader035/viewer/2022062803/56649f285503460f94c4042a/html5/thumbnails/3.jpg)
4.04.02.0
3.03.04.0
1.06.03.0
Markov ChainMarkov Chain
What if we know today and yesterday’s weather?
![Page 4: Advanced Computer Graphics (Fall 2010) CS 283, Lecture 26 Texture Synthesis Ravi Ramamoorthi cs283/fa10 Slides, lecture.](https://reader035.fdocuments.in/reader035/viewer/2022062803/56649f285503460f94c4042a/html5/thumbnails/4.jpg)
Text SynthesisText Synthesis [Shannon,’48] proposed a way to generate
English-looking text using N-grams: Assume a generalized Markov model Use a large text to compute prob.
distributions of each letter given N-1 previous letters
Starting from a seed repeatedly sample this Markov chain to generate new letters
Also works for whole words
WE NEED TO EAT CAKE
![Page 5: Advanced Computer Graphics (Fall 2010) CS 283, Lecture 26 Texture Synthesis Ravi Ramamoorthi cs283/fa10 Slides, lecture.](https://reader035.fdocuments.in/reader035/viewer/2022062803/56649f285503460f94c4042a/html5/thumbnails/5.jpg)
Mark V. Shaney (Bell Labs)Mark V. Shaney (Bell Labs)
Results (using alt.singles corpus): “As I've commented before, really relating
to someone involves standing next to impossible.”
“One morning I shot an elephant in my arms and kissed him.”
“I spent an interesting evening recently with a grain of salt”
![Page 6: Advanced Computer Graphics (Fall 2010) CS 283, Lecture 26 Texture Synthesis Ravi Ramamoorthi cs283/fa10 Slides, lecture.](https://reader035.fdocuments.in/reader035/viewer/2022062803/56649f285503460f94c4042a/html5/thumbnails/6.jpg)
Texture
• Texture depicts spatially repeating patterns
• Many natural phenomena are textures
radishes rocks yogurt
![Page 7: Advanced Computer Graphics (Fall 2010) CS 283, Lecture 26 Texture Synthesis Ravi Ramamoorthi cs283/fa10 Slides, lecture.](https://reader035.fdocuments.in/reader035/viewer/2022062803/56649f285503460f94c4042a/html5/thumbnails/7.jpg)
Texture Synthesis• Goal of Texture Synthesis: create new samples of
a given texture• Many applications: virtual environments, hole-
filling, texturing surfaces
![Page 8: Advanced Computer Graphics (Fall 2010) CS 283, Lecture 26 Texture Synthesis Ravi Ramamoorthi cs283/fa10 Slides, lecture.](https://reader035.fdocuments.in/reader035/viewer/2022062803/56649f285503460f94c4042a/html5/thumbnails/8.jpg)
The Challenge
• Need to model the whole spectrum: from repeated to stochastic texture
repeated
stochastic
Both?
![Page 9: Advanced Computer Graphics (Fall 2010) CS 283, Lecture 26 Texture Synthesis Ravi Ramamoorthi cs283/fa10 Slides, lecture.](https://reader035.fdocuments.in/reader035/viewer/2022062803/56649f285503460f94c4042a/html5/thumbnails/9.jpg)
Efros & Leung Algorithm
• Assuming Markov property, compute P(p|N(p))– Building explicit probability tables infeasible
pp
Synthesizing a pixel
non-parametricsampling
Input image
– Instead, we search the input image for all similar neighborhoods — that’s our pdf for p
– To sample from this pdf, just pick one match at random
![Page 10: Advanced Computer Graphics (Fall 2010) CS 283, Lecture 26 Texture Synthesis Ravi Ramamoorthi cs283/fa10 Slides, lecture.](https://reader035.fdocuments.in/reader035/viewer/2022062803/56649f285503460f94c4042a/html5/thumbnails/10.jpg)
Some Details
• Growing is in “onion skin” order– Within each “layer”, pixels with most neighbors are
synthesized first– If no close match can be found, the pixel is not
synthesized until the end
• Using Gaussian-weighted SSD is very important– to make sure the new pixel agrees with its closest
neighbors– Approximates reduction to a smaller neighborhood
window if data is too sparse
![Page 11: Advanced Computer Graphics (Fall 2010) CS 283, Lecture 26 Texture Synthesis Ravi Ramamoorthi cs283/fa10 Slides, lecture.](https://reader035.fdocuments.in/reader035/viewer/2022062803/56649f285503460f94c4042a/html5/thumbnails/11.jpg)
Neighborhood Window
input
![Page 12: Advanced Computer Graphics (Fall 2010) CS 283, Lecture 26 Texture Synthesis Ravi Ramamoorthi cs283/fa10 Slides, lecture.](https://reader035.fdocuments.in/reader035/viewer/2022062803/56649f285503460f94c4042a/html5/thumbnails/12.jpg)
Varying Window Size
Increasing window size
![Page 13: Advanced Computer Graphics (Fall 2010) CS 283, Lecture 26 Texture Synthesis Ravi Ramamoorthi cs283/fa10 Slides, lecture.](https://reader035.fdocuments.in/reader035/viewer/2022062803/56649f285503460f94c4042a/html5/thumbnails/13.jpg)
Synthesis Results
french canvas rafia weave
![Page 14: Advanced Computer Graphics (Fall 2010) CS 283, Lecture 26 Texture Synthesis Ravi Ramamoorthi cs283/fa10 Slides, lecture.](https://reader035.fdocuments.in/reader035/viewer/2022062803/56649f285503460f94c4042a/html5/thumbnails/14.jpg)
More Resultswhite bread brick wall
![Page 15: Advanced Computer Graphics (Fall 2010) CS 283, Lecture 26 Texture Synthesis Ravi Ramamoorthi cs283/fa10 Slides, lecture.](https://reader035.fdocuments.in/reader035/viewer/2022062803/56649f285503460f94c4042a/html5/thumbnails/15.jpg)
Homage to Shannon
![Page 16: Advanced Computer Graphics (Fall 2010) CS 283, Lecture 26 Texture Synthesis Ravi Ramamoorthi cs283/fa10 Slides, lecture.](https://reader035.fdocuments.in/reader035/viewer/2022062803/56649f285503460f94c4042a/html5/thumbnails/16.jpg)
Hole Filling
![Page 17: Advanced Computer Graphics (Fall 2010) CS 283, Lecture 26 Texture Synthesis Ravi Ramamoorthi cs283/fa10 Slides, lecture.](https://reader035.fdocuments.in/reader035/viewer/2022062803/56649f285503460f94c4042a/html5/thumbnails/17.jpg)
Extrapolation
![Page 18: Advanced Computer Graphics (Fall 2010) CS 283, Lecture 26 Texture Synthesis Ravi Ramamoorthi cs283/fa10 Slides, lecture.](https://reader035.fdocuments.in/reader035/viewer/2022062803/56649f285503460f94c4042a/html5/thumbnails/18.jpg)
Summary
• The Efros & Leung algorithm– Very simple– Surprisingly good results– Synthesis is easier than analysis!– …but very slow
![Page 19: Advanced Computer Graphics (Fall 2010) CS 283, Lecture 26 Texture Synthesis Ravi Ramamoorthi cs283/fa10 Slides, lecture.](https://reader035.fdocuments.in/reader035/viewer/2022062803/56649f285503460f94c4042a/html5/thumbnails/19.jpg)
pp
Image Quilting [Efros & Freeman]
• Observation: neighbor pixels are highly correlated
Input image
non-parametricsampling
BB
Idea:Idea: unit of synthesis = block unit of synthesis = block• Exactly the same but now we want P(B|N(B))
• Much faster: synthesize all pixels in a block at once
• Not the same as multi-scale!
Synthesizing a block
![Page 20: Advanced Computer Graphics (Fall 2010) CS 283, Lecture 26 Texture Synthesis Ravi Ramamoorthi cs283/fa10 Slides, lecture.](https://reader035.fdocuments.in/reader035/viewer/2022062803/56649f285503460f94c4042a/html5/thumbnails/20.jpg)
Input texture
B1 B2
Random placement of blocks
block
B1 B2
Neighboring blocksconstrained by overlap
B1 B2
Minimal errorboundary cut
![Page 21: Advanced Computer Graphics (Fall 2010) CS 283, Lecture 26 Texture Synthesis Ravi Ramamoorthi cs283/fa10 Slides, lecture.](https://reader035.fdocuments.in/reader035/viewer/2022062803/56649f285503460f94c4042a/html5/thumbnails/21.jpg)
min. error boundary
Minimal error boundary
overlapping blocks vertical boundary
__ ==22
overlap error
![Page 22: Advanced Computer Graphics (Fall 2010) CS 283, Lecture 26 Texture Synthesis Ravi Ramamoorthi cs283/fa10 Slides, lecture.](https://reader035.fdocuments.in/reader035/viewer/2022062803/56649f285503460f94c4042a/html5/thumbnails/22.jpg)
Our Philosophy
• The “Corrupt Professor’s Algorithm”:– Plagiarize as much of the source image as you can– Then try to cover up the evidence
• Rationale: – Texture blocks are by definition correct samples of
texture so problem only connecting them together
![Page 23: Advanced Computer Graphics (Fall 2010) CS 283, Lecture 26 Texture Synthesis Ravi Ramamoorthi cs283/fa10 Slides, lecture.](https://reader035.fdocuments.in/reader035/viewer/2022062803/56649f285503460f94c4042a/html5/thumbnails/23.jpg)
![Page 24: Advanced Computer Graphics (Fall 2010) CS 283, Lecture 26 Texture Synthesis Ravi Ramamoorthi cs283/fa10 Slides, lecture.](https://reader035.fdocuments.in/reader035/viewer/2022062803/56649f285503460f94c4042a/html5/thumbnails/24.jpg)
![Page 25: Advanced Computer Graphics (Fall 2010) CS 283, Lecture 26 Texture Synthesis Ravi Ramamoorthi cs283/fa10 Slides, lecture.](https://reader035.fdocuments.in/reader035/viewer/2022062803/56649f285503460f94c4042a/html5/thumbnails/25.jpg)
![Page 26: Advanced Computer Graphics (Fall 2010) CS 283, Lecture 26 Texture Synthesis Ravi Ramamoorthi cs283/fa10 Slides, lecture.](https://reader035.fdocuments.in/reader035/viewer/2022062803/56649f285503460f94c4042a/html5/thumbnails/26.jpg)
![Page 27: Advanced Computer Graphics (Fall 2010) CS 283, Lecture 26 Texture Synthesis Ravi Ramamoorthi cs283/fa10 Slides, lecture.](https://reader035.fdocuments.in/reader035/viewer/2022062803/56649f285503460f94c4042a/html5/thumbnails/27.jpg)
![Page 28: Advanced Computer Graphics (Fall 2010) CS 283, Lecture 26 Texture Synthesis Ravi Ramamoorthi cs283/fa10 Slides, lecture.](https://reader035.fdocuments.in/reader035/viewer/2022062803/56649f285503460f94c4042a/html5/thumbnails/28.jpg)
![Page 29: Advanced Computer Graphics (Fall 2010) CS 283, Lecture 26 Texture Synthesis Ravi Ramamoorthi cs283/fa10 Slides, lecture.](https://reader035.fdocuments.in/reader035/viewer/2022062803/56649f285503460f94c4042a/html5/thumbnails/29.jpg)
Failures
(Chernobyl
Harvest)
![Page 30: Advanced Computer Graphics (Fall 2010) CS 283, Lecture 26 Texture Synthesis Ravi Ramamoorthi cs283/fa10 Slides, lecture.](https://reader035.fdocuments.in/reader035/viewer/2022062803/56649f285503460f94c4042a/html5/thumbnails/30.jpg)
input image
Portilla & Simoncelli
Wei & Levoy Our algorithm
Xu, Guo & Shum
![Page 31: Advanced Computer Graphics (Fall 2010) CS 283, Lecture 26 Texture Synthesis Ravi Ramamoorthi cs283/fa10 Slides, lecture.](https://reader035.fdocuments.in/reader035/viewer/2022062803/56649f285503460f94c4042a/html5/thumbnails/31.jpg)
Portilla & Simoncelli
Wei & Levoy Our algorithm
Xu, Guo & Shum
input image
![Page 32: Advanced Computer Graphics (Fall 2010) CS 283, Lecture 26 Texture Synthesis Ravi Ramamoorthi cs283/fa10 Slides, lecture.](https://reader035.fdocuments.in/reader035/viewer/2022062803/56649f285503460f94c4042a/html5/thumbnails/32.jpg)
Portilla & Simoncelli
Wei & Levoy Our algorithm
input image
Xu, Guo & Shum
![Page 33: Advanced Computer Graphics (Fall 2010) CS 283, Lecture 26 Texture Synthesis Ravi Ramamoorthi cs283/fa10 Slides, lecture.](https://reader035.fdocuments.in/reader035/viewer/2022062803/56649f285503460f94c4042a/html5/thumbnails/33.jpg)
Political Texture Synthesis!
![Page 34: Advanced Computer Graphics (Fall 2010) CS 283, Lecture 26 Texture Synthesis Ravi Ramamoorthi cs283/fa10 Slides, lecture.](https://reader035.fdocuments.in/reader035/viewer/2022062803/56649f285503460f94c4042a/html5/thumbnails/34.jpg)
Fill Order
• In what order should we fill the pixels?
![Page 35: Advanced Computer Graphics (Fall 2010) CS 283, Lecture 26 Texture Synthesis Ravi Ramamoorthi cs283/fa10 Slides, lecture.](https://reader035.fdocuments.in/reader035/viewer/2022062803/56649f285503460f94c4042a/html5/thumbnails/35.jpg)
Fill Order
• In what order should we fill the pixels?– choose pixels that have more neighbors filled
– choose pixels that are continuations of lines/curves/edgesCriminisi, Perez, and Toyama. “Object Removal by Exemplar-based Inpainting,” Proc. CVPR, 2003.
![Page 36: Advanced Computer Graphics (Fall 2010) CS 283, Lecture 26 Texture Synthesis Ravi Ramamoorthi cs283/fa10 Slides, lecture.](https://reader035.fdocuments.in/reader035/viewer/2022062803/56649f285503460f94c4042a/html5/thumbnails/36.jpg)
Exemplar-based Inpainting demo
http://research.microsoft.com/vision/cambridge/i3l/patchworks.htm
![Page 37: Advanced Computer Graphics (Fall 2010) CS 283, Lecture 26 Texture Synthesis Ravi Ramamoorthi cs283/fa10 Slides, lecture.](https://reader035.fdocuments.in/reader035/viewer/2022062803/56649f285503460f94c4042a/html5/thumbnails/37.jpg)
++ ==
Application: Texture Transfer
• Try to explain one object with bits and pieces of another object:
![Page 38: Advanced Computer Graphics (Fall 2010) CS 283, Lecture 26 Texture Synthesis Ravi Ramamoorthi cs283/fa10 Slides, lecture.](https://reader035.fdocuments.in/reader035/viewer/2022062803/56649f285503460f94c4042a/html5/thumbnails/38.jpg)
Texture Transfer Constraint
Texture sample
![Page 39: Advanced Computer Graphics (Fall 2010) CS 283, Lecture 26 Texture Synthesis Ravi Ramamoorthi cs283/fa10 Slides, lecture.](https://reader035.fdocuments.in/reader035/viewer/2022062803/56649f285503460f94c4042a/html5/thumbnails/39.jpg)
• Take the texture from one image and “paint” it onto another object
Texture Transfer
Same as texture synthesis, except an additional constraint:1. Consistency of texture 2. Similarity to the image being “explained”
![Page 40: Advanced Computer Graphics (Fall 2010) CS 283, Lecture 26 Texture Synthesis Ravi Ramamoorthi cs283/fa10 Slides, lecture.](https://reader035.fdocuments.in/reader035/viewer/2022062803/56649f285503460f94c4042a/html5/thumbnails/40.jpg)
==++
![Page 41: Advanced Computer Graphics (Fall 2010) CS 283, Lecture 26 Texture Synthesis Ravi Ramamoorthi cs283/fa10 Slides, lecture.](https://reader035.fdocuments.in/reader035/viewer/2022062803/56649f285503460f94c4042a/html5/thumbnails/41.jpg)
![Page 42: Advanced Computer Graphics (Fall 2010) CS 283, Lecture 26 Texture Synthesis Ravi Ramamoorthi cs283/fa10 Slides, lecture.](https://reader035.fdocuments.in/reader035/viewer/2022062803/56649f285503460f94c4042a/html5/thumbnails/42.jpg)
Image Analogies
Aaron Hertzmann1,2
Chuck Jacobs2
Nuria Oliver2
Brian Curless3
David Salesin2,3
1New York University2Microsoft Research3University of Washington
![Page 43: Advanced Computer Graphics (Fall 2010) CS 283, Lecture 26 Texture Synthesis Ravi Ramamoorthi cs283/fa10 Slides, lecture.](https://reader035.fdocuments.in/reader035/viewer/2022062803/56649f285503460f94c4042a/html5/thumbnails/43.jpg)
Image Analogies
A A’
B B’
![Page 44: Advanced Computer Graphics (Fall 2010) CS 283, Lecture 26 Texture Synthesis Ravi Ramamoorthi cs283/fa10 Slides, lecture.](https://reader035.fdocuments.in/reader035/viewer/2022062803/56649f285503460f94c4042a/html5/thumbnails/44.jpg)
![Page 45: Advanced Computer Graphics (Fall 2010) CS 283, Lecture 26 Texture Synthesis Ravi Ramamoorthi cs283/fa10 Slides, lecture.](https://reader035.fdocuments.in/reader035/viewer/2022062803/56649f285503460f94c4042a/html5/thumbnails/45.jpg)
Blur Filter
![Page 46: Advanced Computer Graphics (Fall 2010) CS 283, Lecture 26 Texture Synthesis Ravi Ramamoorthi cs283/fa10 Slides, lecture.](https://reader035.fdocuments.in/reader035/viewer/2022062803/56649f285503460f94c4042a/html5/thumbnails/46.jpg)
Edge Filter
![Page 47: Advanced Computer Graphics (Fall 2010) CS 283, Lecture 26 Texture Synthesis Ravi Ramamoorthi cs283/fa10 Slides, lecture.](https://reader035.fdocuments.in/reader035/viewer/2022062803/56649f285503460f94c4042a/html5/thumbnails/47.jpg)
A A’
B B’
Artistic Filters
![Page 48: Advanced Computer Graphics (Fall 2010) CS 283, Lecture 26 Texture Synthesis Ravi Ramamoorthi cs283/fa10 Slides, lecture.](https://reader035.fdocuments.in/reader035/viewer/2022062803/56649f285503460f94c4042a/html5/thumbnails/48.jpg)
Colorization
![Page 49: Advanced Computer Graphics (Fall 2010) CS 283, Lecture 26 Texture Synthesis Ravi Ramamoorthi cs283/fa10 Slides, lecture.](https://reader035.fdocuments.in/reader035/viewer/2022062803/56649f285503460f94c4042a/html5/thumbnails/49.jpg)
Texture-by-numbers
A A’
B B’
![Page 50: Advanced Computer Graphics (Fall 2010) CS 283, Lecture 26 Texture Synthesis Ravi Ramamoorthi cs283/fa10 Slides, lecture.](https://reader035.fdocuments.in/reader035/viewer/2022062803/56649f285503460f94c4042a/html5/thumbnails/50.jpg)
Super-resolution
A A’
![Page 51: Advanced Computer Graphics (Fall 2010) CS 283, Lecture 26 Texture Synthesis Ravi Ramamoorthi cs283/fa10 Slides, lecture.](https://reader035.fdocuments.in/reader035/viewer/2022062803/56649f285503460f94c4042a/html5/thumbnails/51.jpg)
Super-resolution (result!)
B B’
![Page 52: Advanced Computer Graphics (Fall 2010) CS 283, Lecture 26 Texture Synthesis Ravi Ramamoorthi cs283/fa10 Slides, lecture.](https://reader035.fdocuments.in/reader035/viewer/2022062803/56649f285503460f94c4042a/html5/thumbnails/52.jpg)
Video Textures
Arno SchödlRichard Szeliski
David SalesinIrfan Essa
Microsoft Research, Georgia Tech
![Page 53: Advanced Computer Graphics (Fall 2010) CS 283, Lecture 26 Texture Synthesis Ravi Ramamoorthi cs283/fa10 Slides, lecture.](https://reader035.fdocuments.in/reader035/viewer/2022062803/56649f285503460f94c4042a/html5/thumbnails/53.jpg)
Problem statement
video clip video texture
![Page 54: Advanced Computer Graphics (Fall 2010) CS 283, Lecture 26 Texture Synthesis Ravi Ramamoorthi cs283/fa10 Slides, lecture.](https://reader035.fdocuments.in/reader035/viewer/2022062803/56649f285503460f94c4042a/html5/thumbnails/54.jpg)
Our approach
• How do we find good transitions?
![Page 55: Advanced Computer Graphics (Fall 2010) CS 283, Lecture 26 Texture Synthesis Ravi Ramamoorthi cs283/fa10 Slides, lecture.](https://reader035.fdocuments.in/reader035/viewer/2022062803/56649f285503460f94c4042a/html5/thumbnails/55.jpg)
Finding good transitions
• Compute L2 distance Di, j between all
frames
Similar frames make good transitions
frame ivs.
frame j
![Page 56: Advanced Computer Graphics (Fall 2010) CS 283, Lecture 26 Texture Synthesis Ravi Ramamoorthi cs283/fa10 Slides, lecture.](https://reader035.fdocuments.in/reader035/viewer/2022062803/56649f285503460f94c4042a/html5/thumbnails/56.jpg)
Markov chain representation
2 3 41
Similar frames make good transitions
![Page 57: Advanced Computer Graphics (Fall 2010) CS 283, Lecture 26 Texture Synthesis Ravi Ramamoorthi cs283/fa10 Slides, lecture.](https://reader035.fdocuments.in/reader035/viewer/2022062803/56649f285503460f94c4042a/html5/thumbnails/57.jpg)
Transition costs
• Transition from i to j if successor of i is similar to j
• Cost function: Cij = Di+1, j
• i
j
i+ 1
j-1
i j D i+ 1, j
![Page 58: Advanced Computer Graphics (Fall 2010) CS 283, Lecture 26 Texture Synthesis Ravi Ramamoorthi cs283/fa10 Slides, lecture.](https://reader035.fdocuments.in/reader035/viewer/2022062803/56649f285503460f94c4042a/html5/thumbnails/58.jpg)
Transition probabilities
•Probability for transition Pij inversely related to
cost:•Pij ~ exp ( – Cij / 2 )
high low
![Page 59: Advanced Computer Graphics (Fall 2010) CS 283, Lecture 26 Texture Synthesis Ravi Ramamoorthi cs283/fa10 Slides, lecture.](https://reader035.fdocuments.in/reader035/viewer/2022062803/56649f285503460f94c4042a/html5/thumbnails/59.jpg)
Example
![Page 60: Advanced Computer Graphics (Fall 2010) CS 283, Lecture 26 Texture Synthesis Ravi Ramamoorthi cs283/fa10 Slides, lecture.](https://reader035.fdocuments.in/reader035/viewer/2022062803/56649f285503460f94c4042a/html5/thumbnails/60.jpg)
Example