Компании
<<  IPhone 4 new IPhone 4G  >>
New course focus
New course focus
Matting, Transparency, and Illumination
Matting, Transparency, and Illumination
How does Superman fly
How does Superman fly
Physics of Alpha Matting
Physics of Alpha Matting
alpha channel
alpha channel
Multiple Alpha Blending
Multiple Alpha Blending
“Pulling a Matte”
“Pulling a Matte”
Average/Median Image
Average/Median Image
-
-
Crowd Synthesis (with Pooja Nath)
Crowd Synthesis (with Pooja Nath)
Background Subtraction
Background Subtraction
Blue Screen
Blue Screen
Blue Screen matting
Blue Screen matting
The Ultimatte
The Ultimatte
Blue screen for superman
Blue screen for superman
Semi-transparent mattes
Semi-transparent mattes
Matting Problem: Mathematical Definition
Matting Problem: Mathematical Definition
Why is general matting hard
Why is general matting hard
Solution #1: No Blue
Solution #1: No Blue
Solution #2: Gray or Flesh
Solution #2: Gray or Flesh
Triangulation Matting (Smith & Blinn)
Triangulation Matting (Smith & Blinn)
The Algorithm
The Algorithm
Triangulation Matting Examples
Triangulation Matting Examples
More Examples
More Examples
More examples
More examples
Problems with Matting
Problems with Matting
Environment Matting and Compositing
Environment Matting and Compositing
Environment Matting Equation
Environment Matting Equation
Explanation of F
Explanation of F
Environment Mattes
Environment Mattes
Performance
Performance
How much better is Environment Matting
How much better is Environment Matting
How much better is Environment Matting
How much better is Environment Matting
Fast Separation of Direct and Global Images Using High Frequency
Fast Separation of Direct and Global Images Using High Frequency
Direct and Global Illumination
Direct and Global Illumination
Direct and Global Components: Interreflections
Direct and Global Components: Interreflections
High Frequency Illumination Pattern
High Frequency Illumination Pattern
High Frequency Illumination Pattern
High Frequency Illumination Pattern
Separation from Two Images
Separation from Two Images
Other Global Effects: Subsurface Scattering
Other Global Effects: Subsurface Scattering
Other Global Effects: Volumetric Scattering
Other Global Effects: Volumetric Scattering
New course focus
New course focus
Scene
Scene
Scene
Scene
More Real World Examples:
More Real World Examples:
Eggs: Diffuse Interreflections
Eggs: Diffuse Interreflections
Wooden Blocks: Specular Interreflections
Wooden Blocks: Specular Interreflections
Kitchen Sink: Volumetric Scattering
Kitchen Sink: Volumetric Scattering
Peppers: Subsurface Scattering
Peppers: Subsurface Scattering
Hand
Hand
Face: Without and With Makeup
Face: Without and With Makeup
Blonde Hair
Blonde Hair
www
www

Презентация на тему: «New course focus». Автор: Alexei Efros. Файл: «New course focus.ppt». Размер zip-архива: 6861 КБ.

New course focus

содержание презентации «New course focus.ppt»
СлайдТекст
1 New course focus

New course focus

Done with texture, patches, and shuffling image content. Focus on light, specifically light models derived from multiple photos of the same scene.

2 Matting, Transparency, and Illumination

Matting, Transparency, and Illumination

cs129: Computational Photography James Hays, Brown, Spring 2011

Slides from Alexei Efros

3 How does Superman fly

How does Superman fly

Super-human powers? OR Image Blending (project 2) OR Image Matting?

4 Physics of Alpha Matting

Physics of Alpha Matting

Semi-transparent objects

Pixels too large

5 alpha channel

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

6 Multiple Alpha Blending

Multiple Alpha Blending

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!)

7 “Pulling a Matte”

“Pulling a Matte”

Problem Definition: 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…

8 Average/Median Image

Average/Median Image

What can we do with this?

9 -

-

=

Background Subtraction

10 Crowd Synthesis (with Pooja Nath)

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

11 Background Subtraction

Background Subtraction

A largely unsolved problem…

One video frame

Estimated background

Difference Image

Thresholded Foreground on blue

12 Blue Screen

Blue Screen

13 Blue Screen matting

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?

14 The Ultimatte

The Ultimatte

p1 and p2

15 Blue screen for superman

Blue screen for superman

16 Semi-transparent mattes

Semi-transparent mattes

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

17 Matting Problem: Mathematical Definition

Matting Problem: Mathematical Definition

18 Why is general matting hard

Why is general matting hard

19 Solution #1: No Blue

Solution #1: No Blue

20 Solution #2: Gray or Flesh

Solution #2: Gray or Flesh

21 Triangulation Matting (Smith & Blinn)

Triangulation Matting (Smith & Blinn)

How many equations? How many unknowns? Does the background need to be constant color?

22 The Algorithm

The Algorithm

23 Triangulation Matting Examples

Triangulation Matting Examples

24 More Examples

More Examples

25 More examples

More examples

26 Problems with Matting

Problems with Matting

Solution: Modify the Matting Equation

Images do not look realistic Lack of Refracted Light Lack of Reflected Light

27 Environment Matting and Compositing

Environment Matting and Compositing

slides by Jay Hetler Douglas E. Zongker ~ Dawn M. Werner ~ Brian Curless ~ David H. Salsin SIGGRAPH 99

28 Environment Matting Equation

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

29 Explanation of F

Explanation of F

R – reflectance image T – Texture image

30 Environment Mattes

Environment Mattes

31 Performance

Performance

Calibration Matting: 10-20 minutes extraction time for each texture map (Pentium II 400Mhz) Compositing: 4-40 frames per second Real-Time?

32 How much better is Environment Matting

How much better is Environment Matting

Alpha Matte Environment Matte Photograph

33 How much better is Environment Matting

How much better is Environment Matting

Alpha Matte Environment Matte Photograph

34 Fast Separation of Direct and Global Images Using High Frequency

Fast Separation of Direct and Global Images Using High Frequency

Illumination

Ramesh Raskar MERL

Shree K. Nayar Gurunandan G. Krishnan Columbia University

Michael D. Grossberg City College of New York

SIGGRAPH Conference Boston, July 2006 Support: ONR, NSF, MERL

35 Direct and Global Illumination

Direct and Global Illumination

surface

source

P

camera

36 Direct and Global Components: Interreflections

Direct and Global Components: Interreflections

i

surface

source

camera

37 High Frequency Illumination Pattern

High Frequency Illumination Pattern

surface

source

camera

38 High Frequency Illumination Pattern

High Frequency Illumination Pattern

surface

source

camera

fraction of activated source elements

39 Separation from Two Images

Separation from Two Images

direct

global

40 Other Global Effects: Subsurface Scattering

Other Global Effects: Subsurface Scattering

translucent surface

source

camera

41 Other Global Effects: Volumetric Scattering

Other Global Effects: Volumetric Scattering

participating medium

surface

source

camera

42 New course focus
43 Scene

Scene

44 Scene

Scene

45 More Real World Examples:

More Real World Examples:

46 Eggs: Diffuse Interreflections

Eggs: Diffuse Interreflections

47 Wooden Blocks: Specular Interreflections

Wooden Blocks: Specular Interreflections

48 Kitchen Sink: Volumetric Scattering

Kitchen Sink: Volumetric Scattering

Volumetric Scattering: Chandrasekar 50, Ishimaru 78

49 Peppers: Subsurface Scattering

Peppers: Subsurface Scattering

50 Hand

Hand

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

51 Face: Without and With Makeup

Face: Without and With Makeup

Without Makeup

With Makeup

52 Blonde Hair

Blonde Hair

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

53 www

www

cs.columbia.edu/CAVE

«New course focus»
http://900igr.net/prezentacija/ekonomika/new-course-focus-134025.html
cсылка на страницу

Компании

40 презентаций о компаниях
Урок

Экономика

125 тем
Слайды