Image-Based Rendering
David Luebke
University of Virginia
But first…
A funky cactus
Image-Based Rendering
You’ve been learning how to turn
geometric models into images
– Specifically, images of compelling 3D objects
and worlds
Image-based rendering: a relatively new
field of computer graphics devoted to
making images from images
Ex: Quicktime VR
Images with depth
Quicktime VR is really just a 2D
panoramic photograph
– Spin around, zoom in and out
But what if we could assign depth to
parts of the image?
Ex: Tour Into the Picture
Tour Into the Picture
Software for:
– Selecting parts of an image
– Assigning a vanishing point for depth of
background objects
– Assigning depth to foreground objects
– “Painting in” behind objects
Depth per pixel
What if we could assign an exact depth
to every pixel?
Ex: MIT Image-Based Editing system
Depth per pixel continued
What if we had a “camera” that
automatically acquired depth at every
Ex: deltasphere
Ex: Monticello project
General image-based
Can we do anything if we don’t have
depth at every pixel?
– Intuitively, if we had enough images we
should be able to reconstruct new images
from novel viewpoints
– Even without depth information
– This is the problem of pure image-based
A 4-D Light Field
Creating Light Fields
Light Field as an
Array of Images
Fast Rendering of Light
Use Gouraud Shading
Light Field Rendering
Demo of Stanford viewer and light
Spectrum of rendering techniques from
pure IBR to pure geometry
Points in this space:
– Pure IBR: light field/lumigraph
– Depth-per-pixel approaches
Another point: view-based rendering
– Slides at:

Image-Based Rendering David Luebke University of Virginia