Computer Vision, CS766 Staff Instructor: Li Zhang lizh[email protected] TA: Yu-Chi Lai [email protected]

Computer Vision, CS766StaffInstructor: Li [email protected]: Yu-Chi [email protected]

TodayIntroductionAdministrative StuffOverview of the Course

About MeLi Zhang ()Last name pronounced as Jung New FacultyPhD 2005, U of WashingtonResearch Scientist 06-07, Columbia UResearchVision and GraphicsTeachingCS766 Computer VisoinCS559 Computer Graphics

Previous Research Focus3D shape reconstructionFour examples of recovered 3D shapes of a moving face from six video streams

Previous Research Focus3D shape reconstructionApplicationLicensed by SONY for GamesUsed by VA Hospital for Prosthetics

Please tell me about you

PrerequisitesPrerequisitesthese are essential!Data structuresA good working knowledge of C and C++ programming(or willingness/time to pick it up quickly!) Linear algebra Vector calculus

Course does not assume prior imaging experienceno image processing, graphics, etc.

Administrative Stuff4 programming projects 15%, 2-3 weeks each1 final project 40%, 5 weeks, open ended of your choosing, but needs project proposal after 1 weekprogress report after 3 weeksFinal presentation after 5 weeksComputer account: Everyone registered in this class will get a Computer Systems Lab account to do project assignments. Email list: [email protected]

Questions?

Every picture tells a storyGoal of computer vision is to write computer programs that can interpret images

Can computer match human perception? Yes and no (but mostly no!)computers can be better at easy things

Can computer match human perception? Yes and no (but mostly no!)computers can be better at easy thingshumans are much better at hard things

Computer Vision vs Human Vision Can do amazing things like:

Recognize people and objectsNavigate through obstaclesUnderstand mood in the scene Imagine stories

But still is not perfect:

Suffers from IllusionsIgnores many detailsAmbiguous description of the worldDoesnt care about accuracy of worldSrinivasa Narasimhans slide

Computer vision vs Human VisionWhat we seeWhat a computer seesSrinivasa Narasimhans slide

Components of a computer vision systemLightingSceneCameraComputerSrinivasa Narasimhans slide

Topics Covered

Cameras and their opticsTodays Digital CamerasThe Camera ObscuraSrinivasa Narasimhans slide

Biological visionHuman EyeMosquito EyeSrinivasa Narasimhans slide

Project 1: High Dynamic Range ImagingCameras have limited dynamic rangeShree Nayars slide

Project 1: High Dynamic Range ImagingLow Dynamic Range ExposuresCombination Yields High Dynamic RangeShree Nayars slide

Image Processing Fourier TransformSampling, ConvolutionImage enhancement Feature detectionSrinivasa Narasimhans slide

Camera Projection

Image TransformationSteve Seitz and Chuck Dyer, View Morphing, SIGGRAPH 1996

Project 2: Panoramic ImagingInput images:Output Image:Steve Seitzs slide

Projective Geometry

Single View Metrologyhttps://research.microsoft.com/vision/cambridge/3d/3dart.htm

Single View Metrologyhttps://research.microsoft.com/vision/cambridge/3d/3dart.htm

Shading and Photometric Stereohttp://www.eecs.harvard.edu/~zickler/helmholtz.html

Texture ModelingrepeatedstochasticSemi-stochastic structuresradishesrocksyogurtAlexei Efros slide

Project 3: Texture SynthesisInputOutputImage Quilting, Efros and Freeman., SIGGRAPH 2002.

Project 3: Texture SynthesisGraphcut Textures, Kwatra et al., SIGGRAPH 2003. Input images:Output Image:

Multi-view GeometryBinocular Stereo (2 classes)Multiview Stereo (1 class)Structure from Motion (2 classes)http://phototour.cs.washington.edu/

Face Detection and Recognition

Project 4: EigenFacesFace detection and recognition

Motion EstimationHidden Dragon Crouching Tiger

Motion EstimationApplicationAndy Serkis, Gollum, Lord of the Rings

Segmentationhttp://www.eecs.berkeley.edu/Research/Projects/CS/vision/bsds/

SegmentationApplicationMedical Image Processing

MattingInputMattingComposition

Light, Color, and Reflection

Capturing Light Field Camera Arrays, Graphics Lab, Stanford University

Capturing Light Field Applications

Structured Light and Ranging Scanninghttp://graphics.stanford.edu/projects/mich/

Structured Light and Ranging Scanninghttp://graphics.stanford.edu/projects/mich/

Structured Light and Ranging Scanninghttp://graphics.stanford.edu/projects/mich/

Novel Cameras and Displayshttp://www1.cs.columbia.edu/CAVE/projects/cc.htm

Course Infohttp://www.cs.wisc.edu/~cs766-1/