The Uncanny Valley in 3D Modeling

1
The Uncanny Valleyin 3D Modeling

• Steve Seitz and Rick Szeliski
• BIRS Workshop onComputer Vision and the Internet
• August 31, 2009

2
The Uncanny Valley

• "The uncanny valley hypothesis holds that when
  robots and other facsimiles of humans look and
  act almost like actual humans, it causes a
  response of revulsion among human observers. The
  "valley" in question is a dip in a proposed graph
  of the positivity of human reaction as a function
  of a robot's lifelikeness. It was introduced by
  Japanese roboticist Masahiro Mori in 1970."
  ltexerpt from Wikipediagt

3
Final Fantasy
4
Polar Express
5
Façade
6
Façade

1. Select building blocks
2. Align them in each image
3. Solve for camera poseand block parameters(using
   constraints)

7
View-dependent texture mapping

1. Determine visible cameras for each surface
   element
2. Blend textures (images) depending on distance
   between original camera and novel viewpoint

8
Model-based stereo

• Compute offset from block model
• Some more results

9
Graz reconstruction
10
Photo Tourism
11
Piecewise planar proxiesSinha, Steedly, Szeliski
ICCV09

• http//research.microsoft.com/en-us/um/redmond/gro
  ups/ivm/PlanarStereo/

12
Reflections
13
Change blindness

• http//www.psych.ubc.ca/rensink/flicker/download/

14
Lightness constancy
15
Image Based Rendering
Output
Image
Real Scene
Synthetic Camera
ImagesModel
Real Cameras -or- Expensive Image Synthesis
16
Graphics/Imaging Continuum
Concentric mosaics
Image centric
Geometry centric
Lumigraph
Light field
Fixed geometry
View-dependent geometry
View-dependent texture
Sprites with depth
LDI
Polygon rendering texture mapping
Interpolation
Warping
17
Video-Based Walkthroughs

• Move camera along a rail (dolly track) and play
  back a 360? video
• Applications
• Homes and architecture
• Outdoor locations(tourist destinations)

18
Surround video acquisition system
OmniCam (six-camera head)
19
OmniCam

• Built by Point Grey Research (Ladybug)
• Six camera head
• Portable hard drives, fiber-optic link
• Resolution per image 1024 x 768
• FOV 100o x 80o
• Acquisition speed 15 fps uncompressed

20
Acquisition platforms

• Robotic cart
• Wearable

21
Video Textures

• How can we turn a short video clipinto an ?
  amount of continuous video?
• dynamic elements in 3D games and presentations
• alternative to 3D graphics animation?
• Schödl, Szeliski, Salesin, Essa, SG2000

22
Video Textures

• Find cyclic structure in the video
• (Optional) region-based analysis
• Play frames with random shuffle
• Smooth over discontinuities (morph)

23
A complete animation