1 / 34

Data-driven Texture Synthesis: Computational Photography

Learn about data-driven methods for texture synthesis in computational photography. Explore the challenges, algorithms, and techniques involved in creating new samples of textures. Discover applications such as virtual environments, hole-filling, and surface texturing.

lpedrick
Download Presentation

Data-driven Texture Synthesis: Computational Photography

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. Data-driven methods: Texture (Sz 10.5) Cs129 Computational Photography James Hays, Brown, Spring 2011 Many slides from Alexei Efros

  2. Texture • Texture depicts spatially repeating patterns • Many natural phenomena are textures radishes rocks yogurt

  3. Texture Synthesis • Goal of Texture Synthesis: create new samples of a given texture • Many applications: virtual environments, hole-filling, texturing surfaces

  4. The Challenge • Need to model the whole spectrum: from repeated to stochastic texture

  5. Efros & Leung Algorithm non-parametric sampling p 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 • Assuming Markov property, compute P(p|N(p)) • Building explicit probability tables infeasible Synthesizing a pixel

  6. 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

  7. Neighborhood Window input

  8. Varying Window Size Increasing window size

  9. Synthesis Results french canvas rafia weave

  10. More Results white bread brick wall

  11. Homage to Shannon

  12. Hole Filling

  13. Extrapolation

  14. Summary • The Efros & Leung algorithm • Very simple • Surprisingly good results • …but very slow

  15. Image Quilting [Efros & Freeman] B p Synthesizing a block • Idea: 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! • Observation: neighbor pixels are highly correlated non-parametric sampling Input image

  16. B1 B1 B2 B2 Neighboring blocks constrained by overlap Minimal error boundary cut block Input texture B1 B2 Random placement of blocks

  17. Minimal error boundary 2 _ = overlap error min. error boundary overlapping blocks vertical boundary

  18. 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

  19. Failures (Chernobyl Harvest)

  20. Portilla & Simoncelli Xu, Guo & Shum input image Wei & Levoy Our algorithm

  21. Portilla & Simoncelli Xu, Guo & Shum input image Wei & Levoy Our algorithm

  22. Portilla & Simoncelli Xu, Guo & Shum input image Wei & Levoy Our algorithm

  23. Political Texture Synthesis!

  24. Application: Texture Transfer • Try to explain one object with bits and pieces of another object: = +

  25. Texture Transfer Constraint Texture sample

  26. Texture Transfer • Take the texture from one image and “paint” it onto another object • Same as texture synthesis, except an additional constraint: • Consistency of texture • Similarity to the image being “explained”

  27. + =

More Related