1 / 29

Announcements

Announcements. Midterm: out by the end of the week Project 1 artifact winners. Global Alignment and Structure from Motion. Today’s Readings Photo Tourism (Snavely et al., SIGGRAPH 2006) http://phototour.cs.washington.edu/Photo_Tourism.pdf. (Adapted from slides by Noah Snavely).

Télécharger la présentation

Announcements

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Announcements • Midterm: out by the end of the week • Project 1 artifact winners

  2. Global Alignment and Structure from Motion • Today’s Readings • Photo Tourism (Snavely et al., SIGGRAPH 2006) • http://phototour.cs.washington.edu/Photo_Tourism.pdf (Adapted from slides by Noah Snavely)

  3. (xn,yn) copy of first image Problem: Drift • Solution • add another copy of first image at the end • this gives a constraint: yn = y1 • there are a bunch of ways to solve this problem • add displacement of (y1 – yn)/(n -1) to each image after the first • compute a global warp: y’ = y + ax • run a big optimization problem, incorporating this constraint • best solution, but more complicated • known as “bundle adjustment” (x1,y1)

  4. t2 Global optimization p2 p1 p3 Input I1 I2 I3 I4 Output t1 t3 t4 (0,0) • We want to estimate ti . We know pi • how do ti relate to pi?

  5. Global optimization p2 r4 s4 r3 s1 p1 p3 q4 q3 q2 I1 I2 I3 I4 • Recipe • Identify the variables you want to estimate • in our case: ti • Identify a set of objectives you want to satisfy • in our case: pi - pj = ti - tj and similar for q, r, s • Define an objective function F over these variables, whose minimum occurs at the “answer” for these variables • Find the minimum of F

  6. Objective function p2 r4 s4 r3 s1 p1 p3 q4 q3 q2 I1 I2 I3 I4 • Objective function • + similar terms for q, r, s

  7. ti= (xi, yi) pi= (ui, vi) Objective function p2 p1 p3 Objective function Matrix form

  8. Objective Function • Adding in q, r, s give a larger matrix equation A x b Defines a least squares problem: minimize • Solution: • Problem: there are multiple solutions for ! (det = 0) • We can add a global offset to a solution and get the same error

  9. Ambiguity in the solution • Each of these solutions has the same error • Called the gauge ambiguity • Solution: fix the translation of one image (t1 = (0,0)) (0,0) (-100,-100) (200,-200)

  10. Computed 3D structure Structure from motion Images on the Internet

  11. minimize p4 g(R,T,P) p1 p3 p2 p5 p7 p6 Structure from motion • aka “bundle adjustment” (texts: Zisserman; Faugeras) Camera 1 Camera 3 R1,t1 R3,t3 Camera 2 R2,t2

  12. SfM objective function • Given point x and rotation and translation R, t • Minimize sum of squared reprojection errors: predicted image location observed image location

  13. Solving structure from motion • Minimizing g is difficult: • g is non-linear due to rotations, perspective division • lots of parameters: 3 for each 3D point, 6 for each camera • difficult to initialize • gauge ambiguity: error is invariant to a similarity transform (translation, rotation, uniform scale) • Many techniques use non-linear least-squares optimization (bundle adjustment) • Levenberg-Marquardt is a popular algorithm • http://en.wikipedia.org/wiki/Levenberg-Marquardt_algorithm • Good code online • Bundler: http://phototour.cs.washington.edu/bundler/ • Multicore: http://grail.cs.washington.edu/projects/mcba/

  14. Photo Tourism • Photo tourism video: http://www.youtube.com/watch?v=5Ji84zb2r8s • Microsoft Photosynth: http://photosynth.net/ • Google Photo Tours: http://maps.google.com/phototours

  15. ?

  16. Reconstructing Rome • In a day... • From ~1M images • Using ~1000 cores • Sameer Agarwal, Noah Snavely, Rick Szeliski, Steve Seitz • http://grail.cs.washington.edu/rome

  17. Coliseum (outside) St. Peters (inside) Coliseum (inside) St. Peters (outside) Il Vittoriano Trevi Fountain Forum

  18. Rome 150K: Colosseum

  19. Rome: St. Peters

  20. Venice (250K images)

  21. Venice: Canal

  22. Dubrovnik

  23. More info • Rome-in-a-day page • http://grail.cs.washington.edu/rome

More Related