1 / 29

Inverse Texture Synthesis

Inverse Texture Synthesis. Li-Yi Wei 1 Jianwei Han 2 Kun Zhou 1 , 2 Hujun Bao 2 Baining Guo 1 Harry Shum 1 1 Microsoft 2 Zhejiang University. Example-based texture synthesis. For a small input texture produce an arbitrarily large output with similar look

xandy
Télécharger la présentation

Inverse Texture Synthesis

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. Inverse Texture Synthesis Li-Yi Wei1 Jianwei Han2 Kun Zhou1,2 Hujun Bao2 Baining Guo1 Harry Shum1 1Microsoft 2Zhejiang University

  2. Example-based texture synthesis • For a small input texture • produce an arbitrarily large output with similar look • Why? may not possible to obtain large input texture synthesis input output

  3. Inverse texture synthesis • From a large input texture • produce a small output that best summarizes input inverse texture synthesis output input

  4. Why? • Textures are getting large • Advances in scanning technology • High dimensionality: time-varying, BRDF • Expensive to store, transmit, compute Yale University MSR Asia Columbia University

  5. Overview inverse texture synthesis input (large) output (small) texturing (fast) texturing (slow) similar quality

  6. Related work: image compression pixel-wise identical compress decompress inverse synth texture synth input perceptual similar

  7. Related work: epitome • Epitome [Jojic et al. 2003] • Jigsaw [Kannan et al. 2007] • Major source of inspiration for us • For general images, not just textures • We provide better quality • Bidirectional similarity [Simakov et al. 2008] • Factoring repeated content [Wang et al. 2008]

  8. Related work: manual crop stationary globally varying original manual crop our result

  9. Globally-varying textures • Markov Random Field (MRF) textures • local & stationary • Globally-varying textures • local, but not necessarily stationary MRF globally varying

  10. Globally varying texturesPrevious work MRF input → globally varying output texture-by-numbers in Image analogies [Hertzmann et al. 2001] progressively variant textures [Zhang et al. 2003] texture design and morphing [Matusik et al. 2005] Globally varying input appearance manifold [Wang et al. 2006] spatially & time varying BRDF [Gu et al. 2006] context-aware texture [Lu et al. 2007]

  11. Globally varying texturesDefinition texture + control maps Examples of control maps user-specified colors [Hertzmann et al. 2001] spatially-varying parameters [Gu et al. 2006] weathering degree-map [Wang et al. 2006] context information [Lu et al. 2007] texture (paint crack) control map (paint thickness)

  12. Globally varying textures Including time-varying textures as well Large data size! time-varying BRDF [Gu et al. 2006] 512 x 512 x 33, 288 MB context-aware texture [Lu et al. 2007] 1226 x 978 x 50, 35 MB

  13. Inverse texture synthesis Compacting globally varying textures including both texture + control map inverse synthesis texture control texture control map input output compaction

  14. Compaction as summary of original • Re-synthesis with user control map faster slower forward synthesis + compaction user control re-synthesis from compaction re-synthesis from original

  15. inverse term (New!) forward term [Kwatra et al. 2005] Basic formulation • Inspired by texture optimization [Kwatra et al. 2005] xp Zp best match zq best match Z (output) xq X (input)

  16. Energy plot energy original compaction size

  17. Why both terms? inverse forward • inverse term preserves all input features • forward term avoids artifacts in compaction both both f-only missing feature i-only garbage both i-only discontinuity

  18. Comparing with epitome [Jojic et al. 2003] • Similar to our method but only inverse term • blur, discontinuity epitome epitome our our original original

  19. Comparing with epitome [Jojic et al. 2003]Re-synthesis epitome epitome our our original original

  20. Solver • How to solve this? • Texture optimization [Kwatra et al. 2005] • Discrete solver [Han et al. 2006]

  21. NO inverse term forward term [Kwatra et al. 2005] zq xq Optimization [Kwatra et al. 2005] • E-step • fix xq • argminz E(x,z) • least square • M-step • fix Z • argminxq |xq-zq|2 • search fix xq xq Zq Z argminxq |xq-zq|2 X

  22. inverse term forward term [Kwatra et al. 2005] zp zq xp xq Our solver • E-step • fix xq • argminz E(x,z) • least square • M-step (forward) • fix Z • argminxq |xq-zq|2 • search xp xq Zq discrete solver [Han et al. 2006] • M-step (inverse) • fix xp • argminzp |xp-zp|2 • discrete solver Z argminxq |xq-zq|2 discrete solver X

  23. Results

  24. GPU synthesis – small texture betterExtension from [Lefebvre & Hoppe 2005] 3 fps, original 6 fps, compact cheese mold 1214 x 1212 1282 3.5 fps, original 7.0 fps, compact dirt 271x481 1282 original compaction

  25. Limitation:Correlation between texture & control texture control original reconstruction compaction

  26. Orientation field for anisotropic textures • Orientation field w as part of energy function • E(x, z) → E(x, z; w) • Good orientation field yields better solution comp. no w comp. with w original orientation field

  27. Future work • Higher dimensional textures • e.g. video • General images, not just textures • Bidirectional similarity [Simakov et al. CVPR 2008] • Image compression

  28. Acknowledgements • Yale graphics group • Columbia graphics group • Sylvain Lefebvre • Hughes Hoppe • Matusik et al. 2005 • Mayang.com • Jiaping Wang • Xin Tong • Jian Sun • Frank Yu • Bennett Wilburn • Eric Stollnitz • Dwight Daniels • Reviewers • Dinesh Manocha • Ming Lin • Chas Boyd • Brandon Lloyd • Avneesh Sud • Billy Chen

  29. Thank You!

More Related