1 / 31

Image Quilting for Texture Synthesis and Transfer

Image Quilting for Texture Synthesis and Transfer. Alexei A. Efros (UC Berkeley) William T. Freeman (MERL) Siggraph01 ’. About author?. Alexei A. Efros Assistant Professor Computer Science Department & The Robotics Institute School of Computer Science

Télécharger la présentation

Image Quilting for Texture Synthesis and Transfer

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. Image Quilting for Texture Synthesis and Transfer Alexei A. Efros (UC Berkeley) William T. Freeman (MERL) Siggraph01’

  2. About author? • Alexei A. Efros • Assistant Professor • Computer Science Department • & The Robotics Institute • School of Computer Science • Carnegie Mellon University • From St. Petersburg, Russia • Got PhD from UC Berkeley in 2003 • Then a year as a Visiting Research Fellow in Visual • Geometry Group of Oxford • Joined in CSD and RI in autumn of 2004 • Computer graphics & computer vision

  3. About author? • William T. Freeman • Professor of Electrical Engineering & • Computer Science at the • Artificial Intelligence • Laboratory at MIT(September, 2001) • Received a BS in physics and MS in electrical • engineering from Stanford (1979), and an MS • in applied physics from Cornell(1981) • Got his PhD in 1992 from the MIT • Worked at Mitsubishi Electric Research Labs (1992 – 2001, • Cambridge) • Computer vision

  4. + = Quilting? Transfer?

  5. Image vs. Texture

  6. Example-based Texture Synthesis Input Example

  7. input image SYNTHESIS True (infinite) texture generated image The Goal of Texture Synthesis Same in perceptual sense

  8. The Challenge • Texture analysis: how to capture the essence of texture? • Need to model the whole spectrum: from repeated to stochastic texture Repeated Stochastic Both?

  9. Related Work • Local region-growing method • -Pixel-based • -Patch-based • Global optimization-based method • Heeger and Bergen sig95,Pyramid-based texture synthesis • Paget and Longstaff IEEE Tran… 98,Texture synthesis via a noncausal nonparametric multiscale markov random field • ….. • Physical Simulation et al

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

  11. 2 _ = overlap error min. error boundary Minimum Error Boundary Cut overlapping blocks vertical boundary

  12. Minimum Error Boundary Cut

  13. The Image Quilting Algorithm • Pick size of block and size of overlap • Synthesize blocks in raster order • Search input texture for block that satisfies overlap constraints (above and left) • Easy to optimize using NN search [Liang et.al., ’01] • Paste new block into resulting texture • Compute minimal error boundary cut

  14. Synthesis Results

  15. Synthesis Results

  16. Synthesis Results

  17. Synthesis Results

  18. Synthesis Results

  19. Synthesis Results

  20. Portilla & Simoncelli Xu, Guo & Shum input image Wei & Levoy Image Quilting

  21. Portilla & Simoncelli Xu, Guo & Shum input image Wei & Levoy Image Quilting

  22. Portilla & Simoncelli Xu, Guo & Shum input image Wei & Levoy Image Quilting

  23. Failures

  24. Image Quilting vs. Graph Cut Input Image Quilting Graph Cut (siggraph 03’)

  25. Luminance Constraint + Texture Transfer

  26. parmesan + = rice + =

  27. Conclusion • No multi-scale, no one-pixel-at-a-time! • fast and very simple • Improved stability • Results are not bad

  28. Thanks a lot! Happy New Year!

  29. Pixel-based Methods • Compare local causal neighbourhoods • Efros and Leung (ICCV ’99) Wei and Levoy (Siggraph 2000) Ashikhmin (I3D 2001) Input Output

  30. Patch-based Methods • Copy patches of pixels rather than single pixels Chaos Mosaic, Xu et al, 1997 Patch-Based Sampling, Liang et al(ACM 2001) Image Quilting, Efros and Williams(Siggraph 2001)

More Related