CS395/495: Spring 2004

1
CS395/495 Spring 2004

• IBMR Image Based Modeling and Rendering
• Introduction
• Jack Tumblin
• jet_at_cs.northwestern.edu

2
Admin How this course works

• Refer to class website (soon)http//www.cs.north
  western.edu/jet/Teach/2004_3spr_IBMR/IBMRsyllabus
  2004.htm
• Tasks
• Reading, lectures, class participation, projects
• Evaluation
• Progressive Programming Project
• Take-Home Midterm
• In-class project demo no final exam

3
GOAL First-Class Primitive

• Want images as first-class primitives
• Useful as BOTH input and output
• Convert to/from traditional scene descriptions
• Want to mix real synthetic scenes freely
• Want to extend photography
• Easily capture sceneshape, movement,
  surface/BRDF, lighting
• Modify Render the captured scene data
• --BUT--
• images hold only PARTIAL scene information
• You cant always get what you want (Mick
  Jagger 1968)

4
Back To Basics Scene Image

• Light 3D Scene
• Illumination, shape, movement, surface BRDF,

2D Image Collection of rays through a point
Image Plane I(x,y)
Position(x,y)
Angle(?,?)
5
Trad. Computer Graphics
2D Image Collection of rays through a point

• Light 3D Scene
• Illumination, shape, movement, surface BRDF,

Reduced, Incomplete Information
Image Plane I(x,y)
Position(x,y)
Angle(?,?)
6
Trad. Computer Vision
2D Image Collection of rays through a point

• Light 3D Scene
• Illumination, shape, movement, surface BRDF,

!TOUGH! ILL-POSED Many Simplifications, External
knowledge
Image Plane I(x,y)
Position(x,y)
Angle(?,?)
7
IBMR Goal Bidirectional Rendering

• Both forward and inverse rendering!

3D Scene Description
?! New Research?
Optical Description
Camera PoseCamera View Geom Scene
illuminationObject shape, positionSurface
reflectance, transparency
Traditional Computer Graphics
2D Display Image(s)
2D Display Image(s)
2D Display Image(s)
2D Display Image(s)
IBMR
8
OLDEST IBR Shadow Maps (1984)

• Fast Shadows from Z-buffer hardware
• 1) Make the Shadow Map
• Render image seen from light source, BUT
• Keep ONLY the Z-buffer values (depth)
• 2) Render Scene from Eyepoint
• Pixel Z depth gives 3D position of surface
• Project 3D position into Shadow map image
• If Shadow Map depth lt 3D depth, SHADOW!

9
Early IBR QuickTime VR (Chen, Williams 93)

• 1) Four Planar Images ? 1 Cylindrical Panorama
• Re-sampling Required!
• Planar Pixels equal distance on x,y plane
  (tan-1?)
• Cylinder Pixs horiz equal angle on cylinder
  (?) vert equal distance on y (tan-1?)

10
Early IBR QuickTime VR (Chen, Williams 93)

• 1) Four Planar Images ? 1 Cylindrical Panorama

IN OUT
11
Early IBR QuickTime VR (Chen, Williams 93)

• 2) Windowing, Horizontal-only Reprojection

IN OUT
12
Early IBR QuickTime VR (Chen, Williams 93)

• 2) Windowing, Horizontal-only Reprojection

IN OUT
13
View Interpolation How?

• But what if no depth is available?
• Traditional Stereo Disparity Map
  pixel-by-pixel search for correspondence

14
View Interpolation How?

• Store Depth at each pixel reproject
• Coarse or Simple 3D model

15
Plenoptic Array The Matrix Effect

• Brute force!Simple arc, line, or ring array of
  cameras
• Synchronized shutter http//www.ruffy.com/firingli
  ne.html
• Warp/blend between images to change viewpoint on
  time-frozen scene

16
Plenoptic Function (Adelson, Bergen 91)

• for a given scene, describe ALL rays through
• ALL pixels, of
• ALL cameras, at
• ALL wavelengths,
• ALL time
• F(x,y,z, ?,?, ?, t)
• Eyeballs Everywhere function (5-D x 2-D!)

17
Seitz View Morphing SIGG96

• http//www.cs.washington.edu/homes/seitz/vmorph/v
  morph.htm
• 1)Manually set some
• corresp.points
• (eye corners, etc.)
• 2) pre-warp and
• post-warp to match
• points in 3D,
• 3) Reproject for
• Virtual cameras

18
Seitz View Morphing SIGG96

• http//www.cs.washington.edu/homes/seitz/vmorph/vm
  orph.htm

19
Seitz View Morphing SIGG96

• http//www.cs.washington.edu/homes/seitz/vmorph/vm
  orph.htm

20
Seitz View Morphing SIGG96

• http//www.cs.washington.edu/homes/seitz/vmorph/vm
  orph.htm

21
Seitz View Morphing SIGG96

• http//www.cs.washington.edu/homes/seitz/vmorph/vm
  orph.htm

22
Scene causes Light Field

• Light field holds all outgoing light rays

Shape, Position, Movement,
Emitted Light
Reflected, Scattered, Light
BRDF, Texture, Scattering
Cameras capture subset of these rays.
23
? Can we recover Shape ?

• Can you find ray intersections? Or ray depth?

Ray colors might not match for non-diffuse
materials (BRDF)
24
? Can we recover Surface Material ?

• Can you find ray intersections? Or ray depth?

Ray colors might not match for non-diffuse
materials (BRDF)
25
Hey, wait

• Light field describes light LEAVING the enclosing
  surface.
• ? Isnt there a complementary light field for
  the light ENTERING the surface?
• YES Image-Based Lighting too!

26
Full 8-D Light Field (10-D, actually time, ?)

• Cleaner Formulation
• Orthographic camera,
• positioned on sphere around object/scene
• Orthographic projector,
• positioned on spherearound object/scene
• F(xc,yc,?c,?c,xl,yl ?l,?l, ?, t)

camera
27
Full 8-D Light Field (10-D, actually time, ?)

• Cleaner Formulation
• Orthographic camera,
• positioned on sphere around object/scene
• Orthographic projector,
• positioned on spherearound object/scene
• F(xc,yc,?c,?c,xl,yl ?l,?l, ?, t)

camera
?c
?c
28
Full 8-D Light Field (10-D, actually time, ?)

• Cleaner Formulation
• Orthographic camera,
• positioned on sphere around object/scene
• Orthographic projector,
• positioned on spherearound object/scene
• F(xc,yc,?c,?c,xl,yl ?l,?l, ?, t)

camera
Projector (laser brick)
29
Full 8-D Light Field (10-D, actually time, ?)

• Cleaner Formulation
• Orthographic camera,
• positioned on sphere around object/scene
• Orthographic projector,
• positioned on spherearound object/scene
• (and wavelength and time)
• F(xc,yc,?c,?c,xl,yl ?l,?l, ?, t)

camera
projector
30
Full 8-D Light Field (10-D, actually time, ?)

• Cleaner Formulation
• Orthographic camera,
• positioned on sphere around object/scene
• Orthographic projector,
• positioned on spherearound object/scene
• (and wavelength and time)
• F(xc,yc,?c,?c,xl,yl ?l,?l, ?, t)

camera
projector
31
Full 8-D Light Field (10-D, actually time, ?)

• ! Complete !
• Geometry, Lighting, BRDF, ! NOT REQUIRED !
• Preposterously Huge (?!?! 8-D function
  sampled at image resolution !?!?), but
• Hugely Redundant
• Wavelength?RGB triplets, ignore Time, and
  Restrict eyepoint movement maybe 3 or 4D ?
• Very Similar imagesuse Warping rules? (SIGG2002)
• Exploit Movie Storage/Compression Methods?

32
IBR-Motivating Opinions

• Computer Graphics Hard
• Complex! geometry, texture, lighting, shadows,
  compositing, BRDF, interreflections, etc. etc.,
  etc.,
• Irregular! Visibility,Topology, Render Eqn.,
• Isolated! Tough to use real objects in CGI
• Slow! compute-bound, off-line only,
• Digital Imaging Easy
• Simple! More quality? Just pump more pixels!
• Regular! Vectorized, compressible, pipelined
• Accessible! Use real OR synthetic (CGI) images!
• Fast! Scalable, Image reuse, a path to
  interactivity

33
Practical IBMR

• What useful partial solutions are possible?
• Texture Maps Panoramas, Env. Maps
• Image(s)Depth (3D shell)
• Estimating Depth Recovering Silhouettes
• Light Probe measures real-world light
• Structured Light to Recover Surfaces
• Hybrids BTF, stitching,

34
Conclusion

• Heavy overlap with computer vision careful not
  to re-invent re-name!
• Elegant Geometry is at the heart of it all, even
  surface reflectance, illumination, etc. etc.
• THUS well dive into geometry--all the rest is
  built on it!