CSL 859: Advanced Computer Graphics

1
CSL 859 Advanced Computer Graphics

• Dept of Computer Sc. Engg.
• IIT Delhi

2
Image-Based Rendering

• So far
• Geometry -gt images
• Object space model, even volumetric
• Image-based rendering
• Image -gt Another image
• Zoom, Pan etc.
• Just image processing?

3
Images with depth

• Quicktime VR
• 2D panoramic photograph
• Spin around, zoom in and out
• Can add objects closer to viewer
• Tour into the picture
• Assign depth to parts of the image
• One might add objects hidden behind some object
  in the image
• Layered depth images

4
Image Based Rendering

• Store image from every conceivable view
• Rendering would reduce to database query
• Generality demand infinite sized database
• Could store enough images
• Given a desired viewpoint (viewmatrix)
• Choose an image from a saved view near the
  desired view
• Warp the image
• Or, interpolate from nearby known viewpoints

5
Ray Equation
6
Correspondence
7
General 3D Warp
Courtesy L Mcmillan
8
Occlusion Determination

• Project the desired center-of-projection onto the
  reference image

9
Occlusion Determination

• Draw towards the projected point
• Guarantees painters ordering
• Independent of the scene's contents
• Generalizes to non-planar viewing surfaces

10
Reconstruction
11
Radiances in a Scene

• Account for all rays
• Origin
• 3 dimensions
• Direction
• 2 dimensions
• Space of rays is 5 dimensional

12
Panorama
All rays from a single point
13
Plenoptic Function
All rays from all points
p P(T, F, x, y, z , ?, t)
Courtesy L. Mcmillan
14
Radiances in a Scene II

• Account for all rays
• Origin
• 3 dimensions
• Direction
• 2 dimensions
• Space of rays is 5 dimensional
• Radiance is constant along ray
• 4 dimensional space
• Subject to occlusion

15
Capturing Radiances

• Capture images from many places
• Camera positioning
• Parameterize the 4D space
• Camera position and 2D image?
• Sample the 4D space
• Coverage and sampling uniformity
• Aliasing
• Too much data

16
Representing Scene Radiance

• Like texture map
• Except ray origin is not fixed
• Source and destination of ray varies
• 2 coordinates (u,v) for ray origin
• 2 coordinates (s,t) for ray destination

v
t
u
s
Light-field Hanrahan Levoy
17
Sampling Coverage
?
?
r
r
18
Stanford Multi-camera Array

• 640 480 pixels 30 fps 128 cameras
• Synchronized timing
• Continuous streaming
• Flexible arrangement

19
Light Field as Array of Images
20
Rendering of Light Fields

• For each pixel (x, y)
• Compute ray
• Map to (u,v,s,t)
• Look up 4D texture
• Store as many 2D textures
• Quadri-linear interpolation

21
Good and Bad

• Advantages
• Simpler computation vs. traditional CG
• Cost independent of scene complexity
• Cost independent of material properties and other
  optical effects
• Disadvantages
• Static geometry
• Fixed lighting
• High storage cost

22
(No Transcript)