Presentation is loading. Please wait.

Presentation is loading. Please wait.

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.

Similar presentations


Presentation on theme: "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."— Presentation transcript:

1

2 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

3 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 input output texture synthesis

4 Inverse texture synthesis From a large input texture produce a small output that best summarizes input input output inverse texture synthesis

5 Yale UniversityColumbia UniversityMSR Asia Why? Textures are getting large Advances in scanning technology High dimensionality: time-varying, BRDF Expensive to store, transmit, compute

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

7 Related work: image compression compress inverse synthtexture synth input decompress pixel-wise identical perceptual similar

8 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]

9 Related work: manual crop our resultmanual croporiginal globally varying stationary

10 Globally-varying textures Markov Random Field (MRF) textures local & stationary Globally-varying textures local, but not necessarily stationary MRFglobally varying

11 Globally varying textures Previous 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]

12 Globally varying textures Definition texture + control mapsExamples 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)

13 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

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

15 Compaction as summary of original Re-synthesis with user control map compaction user control + re-synthesis from compaction forward synthesis re-synthesis from original fasterslower

16 Inverse Texture Synthesis Applicable to MRF textures no control map homogenized result manual cropping ? originalre-synthesis

17 Inverse Texture Synthesis Manual cropping unsuitable for globally variant texture no matter where you put the window original our compactionmanual crop from compactionfrom manual crop blackpurpleorange

18 Basic formulation Inspired by texture optimization [Kwatra et al. 2005] inverse term (New!)forward term [Kwatra et al. 2005] X (input) Z (output) zqzq xqxq best match xpxp ZpZp

19 Energy plot compaction size energy original

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

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

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

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

24 Optimization [Kwatra et al. 2005] X Z NO inverse termforward term [Kwatra et al. 2005] zqzq xqxq xqxq ZqZq E-step fix x q argmin z E(x,z) least square M-step fix Z argmin x q |x q -z q | 2 search fix x q argmin x q |x q -z q | 2

25 Our solver X Z inverse termforward term [Kwatra et al. 2005] E-step fix x q argmin z E(x,z) least square M-step (forward) fix Z argmin x q |x q -z q | 2 search zqzq xqxq xpxp M-step (inverse) fix x p argmin z p |x p -z p | 2 discrete solver xpxp zpzp xqxq ZqZq discrete solver [Han et al. 2006] discrete solver argmin x q |x q -z q | 2

26 Results

27 original (paint crack) 799 x 546 compaction output control from orig sec from comp sec

28 Compaction size on quality 799 x

29 Compaction size on quality 799 x 546 (original)

30 Re-synthesis without control map stationary only original comp. re-synthesis

31 GPU synthesis – small texture better Extension from [Lefebvre & Hoppe 2005] original cheese mold 1214 x 1212 dirt 271x481 compaction fps, original 6 fps, compact 3.5 fps, original 7.0 fps, compact

32 Limitation: Correlation between texture & control original compaction reconstruction texturecontrol

33 Why little squares? Instead of, e.g. a set of texton [Leung & Malik 2001] Most general compaction utilizable for any synthesis algorithm GPU synthesis Looks nice I like little squares visual summary & visualization

34 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 original orientation field comp. no w comp. with w

35 Results: orientation field just mention this in a quick pass original Paris et al. 04 manual + interp ours

36 Results: orientation field original ours Paris et al. 04 manual + interp

37 Results: orientation field original ours Paris et al. 04 manual + interp

38 Results: orientation field original ours Paris et al. 04 manual + interp

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

40 Acknowledgements Yale graphics group Columbia graphics group Sylvain Lefebvre Hughes Hoppe Matusik et al 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

41 Thank You!


Download ppt "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."

Similar presentations


Ads by Google