Presentation is loading. Please wait.

Presentation is loading. Please wait.

Computational Photography, Fall 2013

Similar presentations


Presentation on theme: "Computational Photography, Fall 2013"— Presentation transcript:

1 Computational Photography, Fall 2013
Matting Computational Photography, Fall 2013 Connelly Barnes Slides from Alexei Efros, James Hays

2 How does Superman fly? Super-human powers? OR Image Blending
Image Matting? Matting vs Blending

3 Physics of Alpha Matting
Semi-transparent objects Or, why segmentation isn’t good enough. Pixels too large

4 Alpha channel Add one more channel:
Image(R,G,B,alpha) Sprite! Encodes transparency (or pixel coverage): Alpha = 1: opaque object (complete coverage) Alpha = 0: transparent object (no coverage) 0<Alpha<1: semi-transparent (partial coverage) Example: alpha = 0.7 Partial coverage or semi-transparency

5 Alpha Blending Icomp = aaIa + (1-aa)abIb acomp = aa + (1-aa)ab
So far we assumed that one image (background) is opaque. If blending semi-transparent sprites (the “A over B” operation): Icomp = aaIa + (1-aa)abIb acomp = aa + (1-aa)ab Note: sometimes alpha is premultiplied: im(aR,aG,aB,a): Icomp = Ia + (1-aa)Ib (same for alpha!)

6 Matting an Image Problem Definition: Hard problem
The separation of an image C into A foreground object image Co, a background image Cb, and an alpha matte a Co and a can then be used to composite the foreground object into a different image Hard problem Even if alpha is binary, this is hard to do automatically (background subtraction problem) For movies/TV, manual segmentation of each frame is difficult Need to make a simplifying assumption…

7 Average/Median Image What can we do with this?

8 Background Subtraction
- =

9 Crowd Synthesis (with Pooja Nath)
Do background subtraction in each frame Find and record “blobs” For synthesis, randomly sample the blobs, taking care not to overlap them

10 Background Subtraction
A largely unsolved problem… One video frame Estimated background Difference Image Thresholded Foreground on blue

11 Blue Screen

12 Blue Screen matting Most common form of matting in TV studios & movies
Petros Vlahos invented blue screen matting in the 50s. His Ultimatte® is still the most popular equipment. He won an Oscar for lifetime achievement. A form of background subtraction: Need a known background Compute alpha as SSD(C,Cb) > threshold Or use Vlahos’ formula: a = 1-p1(B-p2G) Hope that foreground object doesn’t look like background no blue ties! Why blue? Why uniform?

13 The Ultimatte p1 and p2

14 Blue screen for superman?

15 Semi-transparent mattes
What we really want is to obtain a true alpha matte, which involves semi-transparency Alpha between 0 and 1

16 Matting Problem: Mathematical Definition

17 Why is general matting hard?

18 Solution #1: No Blue!

19 Solution #2: Gray or Flesh

20 Triangulation Matting (Smith & Blinn)
How many equations? How many unknowns? Does the background need to be constant color?

21 The Algorithm

22 Triangulation Matting Examples

23 More Examples

24 More examples

25 Intelligent Scissors [Mortensen, SIGGRAPH 1995]

26 Intelligent Scissors

27 Intelligent Scissors Initial Cost Matrix

28 Intelligent Scissors Distance from Seed Point (Dynamic Programming)

29 Trimap [Juan and Keriven 2005]

30 Poisson Matting [Sun et al, SIGGRAPH 2004]

31 Poisson Matting Matting Equation (not alpha-premultiplied)

32 Poisson Matting Differentiate. Now what simplifying assumptions can we make?

33 Poisson Matting Approximation. Solve in least square sense

34 Poisson Matting Least squares (variational) problem. Now differentiate again.

35 Poisson Matting Same equation as Project 2 – Poisson Image Editing

36 Poisson Matting Iteratively solve for (1) a, (2) F - B
Poisson Matting Paper

37 Poisson Matting

38 Problems with Matting Solution: Modify the Matting Equation
Images do not look realistic Lack of Refracted Light Lack of Reflected Light Solution: Modify the Matting Equation

39 Environment Matting and Compositing
slides by Jay Hetler Douglas E. Zongker ~ Dawn M. Werner ~ Brian Curless ~ David H. Salsin SIGGRAPH 99

40 Environment Matting Equation
C = F + (1- a)B + F C ~ Color F ~ Foreground color B ~ Background color a ~ Amount of light that passes through the foreground F ~ Contribution of light from Environment that travels through the object Alpha holds values from zero to one…

41 Explanation of F R – reflectance image T – Texture image

42 Series of structured backgrounds
Environment Mattes

43 Performance Calibration
Matting: minutes extraction time for each texture map (Pentium II 400Mhz) Compositing: 4-40 frames per second Real-Time? 3-6 hours

44 How much better is Environment Matting?
Alpha Matte Environment Matte Photograph

45 How much better is Environment Matting?
Alpha Matte Environment Matte Photograph

46 Shree K. Nayar Gurunandan G. Krishnan Columbia University
Fast Separation of Direct and Global Images Using High Frequency Illumination Shree K. Nayar Gurunandan G. Krishnan Columbia University Michael D. Grossberg City College of New York Ramesh Raskar MERL SIGGRAPH Conference Boston, July 2006 Support: ONR, NSF, MERL

47 Direct and Global Illumination
participating medium D : Volumetric translucent surface E E : Diffusion C C : Subsurface A A : Direct surface source B B : Interrelection P camera

48 Direct and Global Components: Interreflections
surface source j BRDF and geometry i camera direct global radiance

49 High Frequency Illumination Pattern
surface source i camera fraction of activated source elements +

50 - High Frequency Illumination Pattern + i surface source camera
fraction of activated source elements

51 Separation from Two Images
direct global

52 Other Global Effects: Subsurface Scattering
translucent surface source i j camera

53 Other Global Effects: Volumetric Scattering
participating medium surface source i j camera

54 Diffuse Interreflections Specular Volumetric Scattering Subsurface Diffusion

55 Scene

56 Scene Direct Global

57 More Real World Examples:

58 Eggs: Diffuse Interreflections
Direct Global

59 Wooden Blocks: Specular Interreflections
Direct Global

60 Kitchen Sink: Volumetric Scattering
Chandrasekar 50, Ishimaru 78 Direct Global

61 Peppers: Subsurface Scattering
Direct Global

62 Hand Direct Global Skin: Hanrahan and Krueger 93,
Uchida 96, Haro 01, Jensen et al. 01, Cula and Dana 02, Igarashi et al. 05, Weyrich et al. 05 Direct Global

63 Face: Without and With Makeup
Without Makeup Global Direct With Makeup

64 Blonde Hair Direct Global Hair Scattering: Stamm et al. 77,
Bustard and Smith 91, Lu et al. 00 Marschner et al. 03 Direct Global

65


Download ppt "Computational Photography, Fall 2013"

Similar presentations


Ads by Google