View%20interpolation%20from%20a%20single%20view

1
View interpolationfrom a single view

• 1. Render object
• 2. Convert Z-buffer to range image
• 3. Re-render from new viewpoint
• 4. Use depths to resolve overlaps
• Q. How to fill in holes?

2
View interpolationfrom multiple views

• 1. Render object from multiple viewpoints
• 2. Convert Z-buffers to range images
• 3. Re-render from new viewpoint
• 4. Use depths to resolve overlaps
• 5. Use multiple views to fill in holes

3
Problems withview interpolation

• resampling the range images
• block moves image interpolation(Chen and
  Williams, 1993)
• splatting with space-variant kernels(McMillan
  and Bishop, 1995)
• fine-grain polygon mesh(McMillan et al., 1997)
• missed objects
• interpolate from available pixels
• use more views

(from Chen and Williams)
4
More problemswith view interpolation

• Obtaining range images is hard!
• use synthetic images(Chen and Williams, 1993)
• epipolar analysis(McMillan and Bishop, 1995)

epipolar geometry
cylindrical epipolar geometry
5
2D image-based rendering
Flythroughs of 3D scenes from pre-acquired 2D
images

• advantages
• low computation compared to classical CG
• cost independent of scene complexity
• imagery from real or virtual scenes
• limitations
• static scene geometry
• fixed lighting
• fixed-look-from or look-at point

6
Apple QuickTime VR

• outward-looking
• panoramic views at regularly spaced
  points
• inward-looking
• views at points on the surface of a sphere

7
A new solutionrebinning old views

• must stay outside convex hull of the object
• like rebinning in computed tomography

8
A light field is anarray of images
9
Spherical 4-DOF gantryfor acquiring light fields

• 0.03 degree positioning error (1mm)
• 0.01 degree aiming error (1 pixel)
• can acquire video while in motion

10
Light field video camera

11
1st generation prototype
12
2nd generation prototype