ICCV05 Contest

1
ICCV05 Contest

• ICCV is the top conference in computer vision. It
  is held once every two years.
• http//research.microsoft.com/szeliski/VisionCont
  est05/

2
Structure from motion

• Given many points in correspondence across
  several images, (uij,vij), simultaneously
  compute the 3D location xi and camera (or motion)
  parameters (K, Rj, tj)
• Two main variants calibrated, and uncalibrated
  (sometimes associated with Euclidean and
  projective reconstructions)

3
Structure from motion

• How many points do we need to match?
• 2 frames
• (R,t) 5 dof 3n point locations ?
• 4n point measurements ?
• n ? 5
• k frames
• 6(k1)-1 3n ? 2kn
• always want to use many more

4
Two-frame methods

• Two main variants
• Calibrated Essential matrix E use ray
  directions (xi, xi )
• Uncalibrated Fundamental matrix F
• Hartley Zisserman 2000

5
Essential matrix

• Co-planarity constraint
• x R x t
• t? x t? R x
• xT t? x x T t? R x
• x T E x 0 with E t? R
• Solve for E using least squares (SVD)
• t is the least singular vector of E
• R obtained from the other two s.v.s

6
Fundamental matrix

• Camera calibrations are unknown
• x F x 0 with F e? H Kt? R K-1
• Solve for F using least squares (SVD)

7
Spacetime Faces High Resolution Capture for
Modeling and Animation

• Li Zhang, Noah Snavely, Brian Curless and Steve
  Seitz
• (SIGGRAPH04)

8
Introduction

• Creating face models that look and move
  realistically is an important problem.
• As usual, given its importance, it is also a
  difficult task.

9
Introduction

• What is missing in Vetter and Blantzs approach?
• limited by the face spanned by the database face
  images
• facial expression and dynamics are not captured
• The goal of this paper from input video
  sequences, generate high resolution, editable and
  dynamically controllable face models

10
How did they do it?