54
Computational Photography CS498dwh Derek Hoiem 8/24/10

Computational Photography CS498dwh

Embed Size (px)

DESCRIPTION

8/24/10. Computational Photography CS498dwh. Derek Hoiem. Today’s Class. A little about me Intro to Computational Photography Course outline and logistics A little about you. About me. Raised in “upstate” NY. About me. 1998-2002 Undergrad at SUNY Buffalo B.S., EE and CSE. 2002-2007 - PowerPoint PPT Presentation

Citation preview

Page 1: Computational Photography CS498dwh

Computational PhotographyCS498dwh

Derek Hoiem

8/24/10

Page 2: Computational Photography CS498dwh

Today’s Class• A little about me• Intro to Computational Photography• Course outline and logistics• A little about you

Page 3: Computational Photography CS498dwh

About me

Raised in “upstate” NY

Page 4: Computational Photography CS498dwh

About me

1998-2002Undergrad at SUNY BuffaloB.S., EE and CSE

2002-2007Grad at Carnegie MellonPh.D. in Robotics

2007-2008Postdoc at Beckman Institute

2009-Assistant Prof in CS at UIUC

Page 5: Computational Photography CS498dwh

My research

Page 6: Computational Photography CS498dwh

Vehicle

wheel

Animal

leg

head Four-legged

Mammal

Move on road Facing right

Can run, jump Is herbivorous Facing right

My Research

Page 7: Computational Photography CS498dwh

My ResearchRecovering 3D layout and context

BED

Page 8: Computational Photography CS498dwh

My Research

Editing images as if they were 3D scenes

Page 9: Computational Photography CS498dwh

My Research

Editing images as if they were 3D scenes

with Kevin Karsch, Varsha Hedau, David Forsyth

Page 10: Computational Photography CS498dwh

Some background to computational photography and …

The Pursuit of Realism

Several of following slides from Alyosha Efros

Page 11: Computational Photography CS498dwh

Depicting Our World: The Beginning

Prehistoric Painting, Lascaux Cave, France~ 15,000 -- 13,000 B.C.

Page 12: Computational Photography CS498dwh

The Empress Theodora with her court. Ravenna, St. Vitale 6th c.

Depicting Our World: Middle Ages

Page 13: Computational Photography CS498dwh

Nuns in Procession. French ms. ca. 1300.

Depicting Our World: Middle Ages

Page 14: Computational Photography CS498dwh

Depicting Our World: RenaissanceEast Doors (1452)North Doors (1424)

Lorenzo Ghiberti(1378-1455)

Page 15: Computational Photography CS498dwh

Depicting Our World: Renaissance

Paolo Uccello,Miracle of the Profaned Host (c.1467-9)

Page 16: Computational Photography CS498dwh

Depicting Our World: Toward Perfection

Jan van Eyck, The Arnolfini Portrait (1426-1434)

Page 17: Computational Photography CS498dwh

Depicting Our World: Toward Perfection

Lens Based Camera Obscura, 1568

Page 18: Computational Photography CS498dwh

Depicting Our World: Perfection!

Still Life, Louis Jaques Mande Daguerre, 1837

Page 19: Computational Photography CS498dwh

But is a photo really realistic?

Page 20: Computational Photography CS498dwh

Is reality what we want?

http://salavon.com

Newlyweds

Page 21: Computational Photography CS498dwh

Better than realism?

http://salavon.com

City (westward)

Page 22: Computational Photography CS498dwh

Enter Computer Graphics...

Page 23: Computational Photography CS498dwh

GRAPHICS

Traditional Computer Graphics

3D geometry

physics

Simulation

projection

Page 24: Computational Photography CS498dwh

Computer graphics

Why so lifeless and sterile?

Page 25: Computational Photography CS498dwh

The richness of our everyday world

Photo by Svetlana Lazebnik

Page 26: Computational Photography CS498dwh

Which parts are hard to model?

Photo by Svetlana Lazebnik

Page 27: Computational Photography CS498dwh

People

From “Final Fantasy”

Alyosha Efros - On the Tube, London

Page 28: Computational Photography CS498dwh

Faces / Hair

Photo by Joaquin Rosales Gomez

From “Final Fantasy”

Page 29: Computational Photography CS498dwh

Urban Scenes

Virtual LA (SGI)

Photo of l LA

Page 30: Computational Photography CS498dwh

Nature

River Cherwell, Oxford

Page 31: Computational Photography CS498dwh

The Realism Spectrum

+ easy to create new worlds+ easy to manipulate objects/viewpoint- very hard to look realistic

+ instantly realistic+ easy to aquire- very hard to manipulate objects/viewpoint

Computer Graphics PhotographyComputationalPhotography

RealismManipulationEase of capture

Page 32: Computational Photography CS498dwh

Computational Photography

How can I use computational techniques to capture light in new ways?

How can I use computational techniques to breathe new life into the photograph?

How can I use computational techniques to synthesize and organize photo collections?

Page 33: Computational Photography CS498dwh

Virtual Real World

Campanile Movie (1997)http://www.debevec.org/Campanile/

Page 34: Computational Photography CS498dwh

Going beyond reality…

http://www.digitaldomain.com/benjamin_button_behind_the_scenes/

Benjamin Button (2008)

Page 35: Computational Photography CS498dwh

Course outline

Prof: Derek Hoiem ([email protected] ), SC3312

Web page:http://www.cs.illinois.edu/class/fa10/cs498dwh/

Page 36: Computational Photography CS498dwh

Course objectives

1. You will have new abilities for visual creation.

Graphic by James Hays

Page 37: Computational Photography CS498dwh

Course objectives

2. You will get a foundation in computer vision.

Safety Health Security

Comfort AccessFun

Page 38: Computational Photography CS498dwh

Course objectives

3. You’ll better appreciate your own visual ability.

Is that a queen or a

bishop?

Page 39: Computational Photography CS498dwh

Course objectives

4. You’ll have fun doing cool stuff!

Page 40: Computational Photography CS498dwh

Projects

Page 41: Computational Photography CS498dwh

Project 1: Hybrid Images

Page 42: Computational Photography CS498dwh

Project 2: Image alignment to Colorize the Prokudin-Gorskii photo collection

Page 43: Computational Photography CS498dwh

Project 3: Poisson Editing

Photos from James Hays

Page 44: Computational Photography CS498dwh

Project 3: Poisson Blending

Photos from Evan Wallace

Page 45: Computational Photography CS498dwh

Project 4: Face morphing

Page 46: Computational Photography CS498dwh

Project 5: Automatic Photo Stitching

Page 47: Computational Photography CS498dwh

Final Project

Something cool!

Page 48: Computational Photography CS498dwh

Project details

• Implement stuff from scratch and apply it to your own photos

• Reporting via web page (plus e-mail code)

• Afterwards, vote for class favorite(s)!

• Software/hardware– Matlab!– Machines available in EWS labs

Page 49: Computational Photography CS498dwh

Getting help outside of class

Office hours• Currently 10-11am Mondays• Otherwise, just stop by. If I’m not there, send me an e-mail.

Discussion board: http://groups.google.com/group/cs498-cp-uiuc

Q&A Guru: Kevin Karsch ([email protected]), graphics lab in 3rd floor SC

Readings/Textbook

Page 50: Computational Photography CS498dwh

Grades• Written and programming assignments (60%)

– More “bells and whistles” required of graduate students• Exam (20%)• Final Projects (20%)• Participation

Late policy• Up to five free days total – use them wisely!• 10% per day after that

Academic Integrity

Page 51: Computational Photography CS498dwh

Other comments

Prerequisites• Linear algebra, plus some basic calculus and

probability• Experience with graphics, image processing, or

Matlab will help but is not necessary

Your own camera• Strongly recommended – can get decent cameras for

reasonable $$$, e.g., Canon IS 1300 ($170)

Page 52: Computational Photography CS498dwh

Feedback

This is a new course, so we’re all learning here. Feedback is welcome.

Page 53: Computational Photography CS498dwh

Introduce yourselves

Page 54: Computational Photography CS498dwh

Final comments

• Reasons to not take the course…

• To do now– Interest in Matlab/Linear Algebra tutorial?– Please fill out the feed-forward forms– Any Q’s or concerns, come talk to me!

• To do later– Look over syllabus, etc.– Sign up for discussion group

• Next class: pixels and basic filtering