10/10: Conclusions Jack Tumblin EECS, Northwestern University The - - PowerPoint PPT Presentation

10 10 conclusions
SMART_READER_LITE
LIVE PREVIEW

10/10: Conclusions Jack Tumblin EECS, Northwestern University The - - PowerPoint PPT Presentation

A Gentle Introduction A Gentle Introduction to Bilateral Filtering to Bilateral Filtering and its Applications and its Applications 10/10: Conclusions Jack Tumblin EECS, Northwestern University The Bilateral Filter The Bilateral Filter


slide-1
SLIDE 1
slide-2
SLIDE 2

A Gentle Introduction to Bilateral Filtering and its Applications A Gentle Introduction to Bilateral Filtering and its Applications

10/10: Conclusions

Jack Tumblin – EECS, Northwestern University

slide-3
SLIDE 3

The Bilateral Filter The Bilateral Filter

  • As Simple as

Weights from TWO Gaussian Functions;

  • Has deep connections to PDE formalisms,

shock-forming, heat flow, and diffusion

  • Speed? several very fast versions
slide-4
SLIDE 4

Bilateral Filter Bilateral Filter

GOALS are Ambitious & Subjective, but GOALS are Ambitious & Subjective, but

  • Noise Removal
  • “Edge-Preserving Smoothing”
  • Locally Weighted Averaging with Outlier Rejection
  • Visual Separation of ‘fine details’ and ‘large features’

METHODS are Simple & Practical METHODS are Simple & Practical

  • Bilateral Filter: doubly-weighted local average,

High weights only for ‘nearby’, ‘similar’ values

  • YOU set parameters of what is ‘nearby’,
  • f what is ‘similar’
slide-5
SLIDE 5

VERY Broad Range of Applications: VERY Broad Range of Applications:

  • any task where ‘edges’ and ‘similarities’

carry useful information

  • data of arbitrary dimensions;

M to N, time, color, image vector-spaces, etc,

  • even on manifolds 3D meshes, etc.
slide-6
SLIDE 6

Explosive Growth: *6* New Papers Here Explosive Growth: *6* New Papers Here

SIGGRAPH 2007: don’t miss these new works! .

  • Image Deblurring with

Blurred/Noisy Image Pairs

  • L. Yuan, et al.
  • Multiscale Shape and Detail Enhancement

from Multi-Light Image Collections

  • R. Fattal et al.
  • Joint Bilateral Upsampling
  • J. Kopf et al.
  • LDR2HDR: On-the-fly Reverse Tone Mapping
  • f Legacy Video and Photographs
  • A. G. Rempel et al.
  • Factored Time-Lapse Video
  • K. Sunkavalli et al.
  • Real-Time Edge-Aware Image Processing

With the Bilateral Grid

  • J. Chen et al.
slide-7
SLIDE 7

Is All the Work Finished? Is All the Work Finished?

  • Nothing left to explore?

No, No, No! Bilateral filters raise deep, basic questions; Answers still vague and tentative.. For example …

slide-8
SLIDE 8

What Is ‘Noise’? What is ‘Texture’? What Is ‘Noise’? What is ‘Texture’?

Wet Sand (Jay Sekora)

slide-9
SLIDE 9

What Is ‘Noise’? What is ‘Texture’? What Is ‘Noise’? What is ‘Texture’?

Human Skin (Ken Perlin)

slide-10
SLIDE 10

What Is an ‘Edge’ in Human Vision? What Is an ‘Edge’ in Human Vision?

Illusory Contours (G. Kanizsa, 1955)

slide-11
SLIDE 11

Does absolute intensity matter? Does absolute intensity matter?

Often, Perceived Intensities ≠ Pixel Values:

Example: Example: ‘ ‘Simultaneous Contrast Simultaneous Contrast’ ’ Center strip has Center strip has CONSTANT CONSTANT intensity intensity… …

slide-12
SLIDE 12

Does absolute intensity matter? Does absolute intensity matter?

Often, Perceived Intensities ≠ Pixel Values:

Example: Example: ‘ ‘Simultaneous Contrast Simultaneous Contrast’ ’ Center strip has Center strip has CONSTANT CONSTANT intensity intensity… …

slide-13
SLIDE 13

What Is an Illumination Edge? What Is an Illumination Edge?

Sometimes it isn’t a large intensity change…

slide-14
SLIDE 14

What Is a ‘Geometric Edge’ in Images? What Is a ‘Geometric Edge’ in Images?

3D ‘Peanut’ shape Some silhouettes are SUGGESTED by shape cues

slide-15
SLIDE 15

What Is an ‘Edge’ at The Finest Scales? What Is an ‘Edge’ at The Finest Scales?

Scale Problems: Can’t resolve every hair and fiber in fur… Long Black Whiskers:

  • Visible on Bkgnd, but
  • Visible against fur?

Albrecht Durer (1502)

slide-16
SLIDE 16

For any perceivable image? For any perceivable image?

Hmm. Edge? Noise? Regions? Texture? Silhouette? …

http://mfrost.typepad.com/cute_overload/2007/02/backlit_extrava.html

slide-17
SLIDE 17

Thank You For Attending! Thank You For Attending!

  • Please do fill out a review form, and

tell us how we can improve the course…

http://www.siggraph.org/courses_evaluation

  • For more in-depth info: links, and all docs:

http://people.csail.mit.edu/sparis/siggraph07_course/

slide-18
SLIDE 18

Course Evaluations Course Evaluations

http://www.siggraph.org/courses_evaluation

4 Random Individuals will win an ATI Radeontm HD2900XT

slide-19
SLIDE 19
slide-20
SLIDE 20