lec11_sfm

lec11_sfm - CS6670:ComputerVision NoahSnavely...

Info iconThis preview shows pages 1–14. Sign up to view the full content.

View Full Document Right Arrow Icon
Lecture 11: Structure from motion CS6670: Computer Vision Noah Snavely
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Announcements Project 2 out, due next Wednesday, October 14 Artifact due Friday, October 16 Questions?
Background image of page 2
Readings Szeliski, Chapter 7.2 My thesis, Chapter 3 http://www.cs.cornell.edu/~snavely/publications/thesis/thesis.pdf
Background image of page 3

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Energy minimization via graph cuts Labels (disparities) d 1 d 2 d 3 edge weight
Background image of page 4
Other uses of graph cuts
Background image of page 5

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Agarwala et al., Interactive Digital Photo Montage, SIGGRAPH 2004 Other uses of graph cuts
Background image of page 6
Panoramic stitching Problem: copy every pixel in the output image from one of the input images (without blending) Make transitions between two images seamless
Background image of page 7

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Panoramic stitching Can be posed as a labeling problem: label each pixel in the output image with one of the input images Input images: Output panorama:
Background image of page 8
Panoramic stitching Number of labels: k = number of input images Objective function (in terms of labeling L ) Input images: Output panorama:
Background image of page 9

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Panoramic stitching Infinite cost of labeling a pixel (x,y) with image I if I doesn’t cover (x,y) Else, cost = 0
Background image of page 10
Photographing long scenes with multi viewpoint panoramas
Background image of page 11

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Today: Drift copy of first image (x n ,y n ) (x 1 ,y 1 ) add another copy of first image at the end this gives a constraint: y n = y 1 there are a bunch of ways to solve this problem add displacement of (y 1 –y n )/(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”
Background image of page 12
Global optimization Minimize a global energy function:
Background image of page 13

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Image of page 14
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 09/27/2010 for the course CS 667 at Cornell.

Page1 / 42

lec11_sfm - CS6670:ComputerVision NoahSnavely...

This preview shows document pages 1 - 14. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online