1	Stereo Guest Lecture by Li Zhang http://www.cs.washington.edu/homes/lizhang/
2	Last lecture: new images from images
3	This lecture: 3D structures from images How might we do this automatically? What cues in the image provide 3D information? Readings Trucco & Verri, Chapter 7 Read through 7.1, 7.2.1, 7.2.2, 7.3.1, 7.3.2, 7.3.7 and 7.4, 7.4.1. The rest is optional.
4	Visual cues Shading
5	Visual cues Shading Texture
6	Visual cues Shading Texture Focus
7	Visual cues Shading Texture Focus Motion
8	Visual cues Shading Texture Focus Motion
9
10
11
12
13
14	Stereograms online UCR stereographs http://www.cmp.ucr.edu/site/exhibitions/stereo/ The Art of Stereo Photography http://www.photostuff.co.uk/stereo.htm History of Stereo Photography http://www.rpi.edu/~ruiz/stereo_history/text/historystereog.html Double Exposure http://home.centurytel.net/s3dcor/index.html Stereo Photography http://www.shortcourses.com/book01/chapter09.htm 3D Photography links http://www.studyweb.com/links/5243.html National Stereoscopic Association http://204.248.144.203/3dLibrary/welcome.html Books on Stereo Photography http://userwww.sfsu.edu/~hl/3d.biblio.html
15	Stereo
16	Stereo
17	Stereo correspondence Determine Pixel Correspondence Pairs of points that correspond to same scene point
18	Stereo image rectification
19	Stereo image rectification reproject image planes onto a common plane parallel to the line between optical centers pixel motion is horizontal after this transformation two homographies (3x3 transform), one for each input image reprojection C. Loop and Z. Zhang. Computing Rectifying Homographies for Stereo Vision. IEEE Conf. Computer Vision and Pattern Recognition, 1999.
20	Stereo matching algorithms Match Pixels in Conjugate Epipolar Lines Assume brightness constancy This is a tough problem Numerous approaches A good survey and evaluation: http://www.middlebury.edu/stereo/
21	Your basic stereo algorithm
22	Window size Smaller window Larger window
23	Stereo results Data from University of Tsukuba Similar results on other images without ground truth
24	Results with window search
25	Better methods exist...
26	Depth from disparity
27	Real-time stereo Used for robot navigation (and other tasks) Several software-based real-time stereo techniques have been developed (most based on simple discrete search)
28	Stereo reconstruction pipeline Steps Calibrate cameras Rectify images Compute disparity Estimate depth
29	Active stereo with structured light Project “structured” light patterns onto the object simplifies the correspondence problem
30	Active stereo with structured light
31	Laser scanning Optical triangulation Project a single stripe of laser light Scan it across the surface of the object This is a very precise version of structured light scanning
32	Laser scanned models
33	Laser scanned models
34	Laser scanned models
35	Laser scanned models
36	Laser scanned models
37	Moving scenes
38
39
40
41
42
43
44	Spacetime stereo matching
45	Non-linear least square
46	Spacetime stereo matching
47	Demos
48