a gentle introduction to bilateral filtering and its applications 10/10: conclusions jack tumblin...
DESCRIPTION
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 versionsTRANSCRIPT
![Page 1: A Gentle Introduction to Bilateral Filtering and its Applications 10/10: Conclusions Jack Tumblin – EECS, Northwestern University](https://reader036.vdocument.in/reader036/viewer/2022062302/5a4d1b4d7f8b9ab0599a62c2/html5/thumbnails/1.jpg)
![Page 2: A Gentle Introduction to Bilateral Filtering and its Applications 10/10: Conclusions Jack Tumblin – EECS, Northwestern University](https://reader036.vdocument.in/reader036/viewer/2022062302/5a4d1b4d7f8b9ab0599a62c2/html5/thumbnails/2.jpg)
A Gentle Introductionto Bilateral Filteringand its Applications
10/10: Conclusions
Jack Tumblin – EECS, Northwestern University
![Page 3: A Gentle Introduction to Bilateral Filtering and its Applications 10/10: Conclusions Jack Tumblin – EECS, Northwestern University](https://reader036.vdocument.in/reader036/viewer/2022062302/5a4d1b4d7f8b9ab0599a62c2/html5/thumbnails/3.jpg)
The Bilateral Filter
• As Simple asWeights from TWO Gaussian Functions;
• Has deep connections to PDE formalisms,shock-forming, heat flow, and diffusion
• Speed? several very fast versions
![Page 4: A Gentle Introduction to Bilateral Filtering and its Applications 10/10: Conclusions Jack Tumblin – EECS, Northwestern University](https://reader036.vdocument.in/reader036/viewer/2022062302/5a4d1b4d7f8b9ab0599a62c2/html5/thumbnails/4.jpg)
Bilateral Filter
GOALS are Ambitious & Subjective, butGOALS 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’,
of what is ‘similar’
![Page 5: A Gentle Introduction to Bilateral Filtering and its Applications 10/10: Conclusions Jack Tumblin – EECS, Northwestern University](https://reader036.vdocument.in/reader036/viewer/2022062302/5a4d1b4d7f8b9ab0599a62c2/html5/thumbnails/5.jpg)
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.
![Page 6: A Gentle Introduction to Bilateral Filtering and its Applications 10/10: Conclusions Jack Tumblin – EECS, Northwestern University](https://reader036.vdocument.in/reader036/viewer/2022062302/5a4d1b4d7f8b9ab0599a62c2/html5/thumbnails/6.jpg)
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
of 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.
![Page 7: A Gentle Introduction to Bilateral Filtering and its Applications 10/10: Conclusions Jack Tumblin – EECS, Northwestern University](https://reader036.vdocument.in/reader036/viewer/2022062302/5a4d1b4d7f8b9ab0599a62c2/html5/thumbnails/7.jpg)
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 …
![Page 8: A Gentle Introduction to Bilateral Filtering and its Applications 10/10: Conclusions Jack Tumblin – EECS, Northwestern University](https://reader036.vdocument.in/reader036/viewer/2022062302/5a4d1b4d7f8b9ab0599a62c2/html5/thumbnails/8.jpg)
What Is ‘Noise’? What is ‘Texture’?
Wet Sand (Jay Sekora)
![Page 9: A Gentle Introduction to Bilateral Filtering and its Applications 10/10: Conclusions Jack Tumblin – EECS, Northwestern University](https://reader036.vdocument.in/reader036/viewer/2022062302/5a4d1b4d7f8b9ab0599a62c2/html5/thumbnails/9.jpg)
What Is ‘Noise’? What is ‘Texture’?
Human Skin (Ken Perlin)
![Page 10: A Gentle Introduction to Bilateral Filtering and its Applications 10/10: Conclusions Jack Tumblin – EECS, Northwestern University](https://reader036.vdocument.in/reader036/viewer/2022062302/5a4d1b4d7f8b9ab0599a62c2/html5/thumbnails/10.jpg)
What Is an ‘Edge’ in Human Vision?
Illusory Contours (G. Kanizsa, 1955)
![Page 11: A Gentle Introduction to Bilateral Filtering and its Applications 10/10: Conclusions Jack Tumblin – EECS, Northwestern University](https://reader036.vdocument.in/reader036/viewer/2022062302/5a4d1b4d7f8b9ab0599a62c2/html5/thumbnails/11.jpg)
Does absolute intensity matter?
Often, Perceived Intensities ≠ Pixel Values:
Example: Example: ‘Simultaneous Contrast’ ‘Simultaneous Contrast’ Center strip has Center strip has CONSTANTCONSTANT intensity… intensity…
![Page 12: A Gentle Introduction to Bilateral Filtering and its Applications 10/10: Conclusions Jack Tumblin – EECS, Northwestern University](https://reader036.vdocument.in/reader036/viewer/2022062302/5a4d1b4d7f8b9ab0599a62c2/html5/thumbnails/12.jpg)
Does absolute intensity matter?
Often, Perceived Intensities ≠ Pixel Values:
Example: Example: ‘Simultaneous Contrast’ ‘Simultaneous Contrast’ Center strip has Center strip has CONSTANTCONSTANT intensity… intensity…
![Page 13: A Gentle Introduction to Bilateral Filtering and its Applications 10/10: Conclusions Jack Tumblin – EECS, Northwestern University](https://reader036.vdocument.in/reader036/viewer/2022062302/5a4d1b4d7f8b9ab0599a62c2/html5/thumbnails/13.jpg)
What Is an Illumination Edge?
Sometimes it isn’t a large intensity change…
![Page 14: A Gentle Introduction to Bilateral Filtering and its Applications 10/10: Conclusions Jack Tumblin – EECS, Northwestern University](https://reader036.vdocument.in/reader036/viewer/2022062302/5a4d1b4d7f8b9ab0599a62c2/html5/thumbnails/14.jpg)
What Is a ‘Geometric Edge’ in Images?
3D ‘Peanut’ shape
Some silhouettes
are SUGGESTED
by shape cues
![Page 15: A Gentle Introduction to Bilateral Filtering and its Applications 10/10: Conclusions Jack Tumblin – EECS, Northwestern University](https://reader036.vdocument.in/reader036/viewer/2022062302/5a4d1b4d7f8b9ab0599a62c2/html5/thumbnails/15.jpg)
What Is an ‘Edge’ at The Finest Scales?
Scale Problems:
Can’t resolve everyhair and fiber in fur…
Long Black Whiskers:
• Visible on Bkgnd, but
• Visible against fur?
Albrecht Durer (1502)
![Page 16: A Gentle Introduction to Bilateral Filtering and its Applications 10/10: Conclusions Jack Tumblin – EECS, Northwestern University](https://reader036.vdocument.in/reader036/viewer/2022062302/5a4d1b4d7f8b9ab0599a62c2/html5/thumbnails/16.jpg)
For any perceivable image?
Hmm.
Edge?Noise?Regions?Texture?Silhouette?…
http://mfrost.typepad.com/cute_overload/2007/02/backlit_extrava.html
![Page 17: A Gentle Introduction to Bilateral Filtering and its Applications 10/10: Conclusions Jack Tumblin – EECS, Northwestern University](https://reader036.vdocument.in/reader036/viewer/2022062302/5a4d1b4d7f8b9ab0599a62c2/html5/thumbnails/17.jpg)
Thank You For Attending!
• Please do fill out a review form, andtell 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/
![Page 18: A Gentle Introduction to Bilateral Filtering and its Applications 10/10: Conclusions Jack Tumblin – EECS, Northwestern University](https://reader036.vdocument.in/reader036/viewer/2022062302/5a4d1b4d7f8b9ab0599a62c2/html5/thumbnails/18.jpg)
Course Evaluations
http://www.siggraph.org/courses_evaluation
4 Random Individuals will win an ATI Radeontm HD2900XT
![Page 19: A Gentle Introduction to Bilateral Filtering and its Applications 10/10: Conclusions Jack Tumblin – EECS, Northwestern University](https://reader036.vdocument.in/reader036/viewer/2022062302/5a4d1b4d7f8b9ab0599a62c2/html5/thumbnails/19.jpg)
![Page 20: A Gentle Introduction to Bilateral Filtering and its Applications 10/10: Conclusions Jack Tumblin – EECS, Northwestern University](https://reader036.vdocument.in/reader036/viewer/2022062302/5a4d1b4d7f8b9ab0599a62c2/html5/thumbnails/20.jpg)
ENDEND