RealTime High Quality Rendering

1
Real-Time High Quality Rendering

• COMS 6160 Fall 2004, Lecture 6
• Image-Based Modeling and Rendering

http//www.cs.columbia.edu/ravir/6160
2
Motivation for Lecture

• IBR is tangentially related to course (more
  pertinent to acquisition of measured materials
  and scenes)
• But many of the rendering methods, especially
  precomputed techniques borrow from it
• And many methods use measured data
• Also, images are an important source for
  rendering

3
Next few slides courtesy Paul Debevec SIGGRAPH
99 course notes
4
(No Transcript)
5
(No Transcript)
6
IBR Pros and Cons

• Advantages
• Easy to capture images photorealistic by
  definition
• Simple, universal representation
• Often bypass geometry estimation?
• Independent of scene complexity?
• Disadvantages
• WYSIWYG but also WYSIAYG
• Explosion of data as flexibility increased
• Often discards intrinsic structure of model?

7
(No Transcript)
8
(No Transcript)
9
IBR A brief history

• Texture maps, bump maps, env. maps 70s
• Poggio et al. MIT Faces, image-based
  analysis/synthesis
• Modern Era
• Chen and Williams 93, View Interpolation Images
  with depth
• Chen 95 Quicktime VR Images from many
  viewpoints
• McMillan and Bishop 95 Plenoptic Modeling Images
  w disparity
• Gortler et al, Levoy and Hanrahan 96 Light Fields
  4D
• Shade et al. 98 Layered Depth Images 2.5D
• Debevec et al. 00 Reflectance Field 4D
• Inverse rendering methods (Sato,Yu,Marschner,Boivi
  n,)
• Fundamentally, sampled representations in
  graphics

10
Outline

• Overview of IBR
• Basic approaches
• Image Warping
• Light Fields
• Survey of some recent work

11
Warping slides courtesy Leonard McMillan
12
(No Transcript)
13
(No Transcript)
14
(No Transcript)
15
(No Transcript)
16
Outline

• Overview of IBR
• Basic approaches
• Image Warping
• 2D depth. Requires correspondence/disparity
• Light Fields 4D
• Survey of some recent work

17
(No Transcript)
18
(No Transcript)
19
(No Transcript)
20
(No Transcript)
21
(No Transcript)
22
(No Transcript)
23
(No Transcript)
24
(No Transcript)
25
(No Transcript)
26
(No Transcript)
27
Outline

• Overview of IBR
• Basic approaches
• Image Warping
• 2D depth. Requires correspondence/disparity
• Light Fields 4D
• Survey of some recent work

28
Refresher LDIs

• Layered depth images Shade et al. 98

Slide from Agrawala, Ramamoorthi, Heirich, Moll,
SIGGRAPH 2000
29
Refresher LDIs

• Layered depth images Shade et al. 98

LDI
30
Refresher LDIs

• Layered depth images Shade et al. 98

LDI
(Depth, Color)
31
(No Transcript)
32
Surface Light Fields

• Miller 98, Nishino 99, Wood 00
• Reflected light field (lumisphere) on surface
• Explicit geometry as against light fields.
  Easier compress

33
Acquiring Reflectance Field of Human Face
Debevec et al. SIGGRAPH 00

• Illuminate subject from many incident directions

34
Example Images
Images from Debevec et al. 00
35
Conclusion (my views)

• Real issue is compactness/flexibility vs.
  rendering speed
• IBR is use of sampled representations. Easy to
  interpolate, fast to render. If samples images,
  easy to acquire.
• Of course, for this course, some pretty fancy
  precomputed algorithms (because we want to handle
  complex lighting that changes)
• IBR in pure form not really practical
• WYSIAYG
• Explosion as increase dimensions (8D transfer
  function)
• Ultimately, compression, flexibility needs
  geometry/materials
• But lots of recent work (some in course) begins
  to correct these issues
• Right question is tradeoff compactness/efficiency
• Factored representations
• Understand sampling rates and reconstruction