1	Texture Synthesis
2	Texture Today’s Reading Alexei A. Efros and Thomas K. Leung, “Texture Synthesis by Non-parametric Sampling,” Proc. International Conference on Computer Vision (ICCV), 1999. http://www.cs.berkeley.edu/~efros/research/NPS/efros-iccv99.pdf
3	Modeling Texture What is texture? How can we model it?
4	Markov Chains Markov Chain a sequence of random variables is the state of the model at time t Markov assumption: each state is dependent only on the previous one dependency given by a conditional probability: The above is actually a first-order Markov chain An N’th-order Markov chain:
5	Markov Chain Example: Text “A dog is a man’s best friend. It’s a dog eat dog world out there.”
6	Text synthesis Create plausible looking poetry, love letters, term papers, etc. Most basic algorithm Build probability histogram find all blocks of N consecutive words/letters in training documents compute probability of occurance Given words compute by sampling from Example on board...
7	[Scientific American, June 1989, Dewdney] “I Spent an Interesting Evening Recently with a Grain of Salt” - Mark V. Shaney (computer-generated contributor to UseNet News group called net.singles)
8	Modeling Texture What is texture? An image obeying some statistical properties Similar structures repeated over and over again Often has some degree of randomness
9	Markov Random Field
10	Texture Synthesis [Efros & Leung, ICCV 99] Can apply 2D version of text synthesis
11	Synthesizing One Pixel What is ? Find all the windows in the image that match the neighborhood consider only pixels in the neighborhood that are already filled in To synthesize x pick one matching window at random assign x to be the center pixel of that window
12	Really Synthesizing One Pixel
13	Growing Texture
14	Window Size Controls Regularity
15	More Synthesis Results
16	More Results
17	Failure Cases
18	Image-Based Text Synthesis
19	Speed Given: image of k² pixels Output: image of n² pixels how many window comparisons does this algorithm require?
20
21
22
23	Texture Transfer
24
25
26
27	Combining two images
28
29	Graph cut setup
30	Graph cut texture synthesis: Video
31	Image Analogies (Hertzmann ’01)
32	Artistic Filters
33	Texture-by-numbers
34	Other applications of Image Analogies Texture synthesis Super-resolution Texture transfer Image colorization Simple filters (blur, emboss) More details: Hertzmann et al., SIGGRAPH 2001 http://mrl.nyu.edu/projects/image-analogies/
35	Applications of Texture Modeling Super-resolution Freeman & Pasztor, 1999 Baker & Kanade, 2000 Image/video compression Texture recognition, segmentation DeBonet Restoration removing scratches, holes, filtering Zhu et al. Art/entertainment