Top Banner
Image-Based Rendering A Brief Overview David Luebke University of Virginia
15

Image-Based Rendering A Brief Overview David Luebke University of Virginia.

Jan 05, 2016

Download

Documents

Laura Harris
Welcome message from author
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
Page 1: Image-Based Rendering A Brief Overview David Luebke University of Virginia.

Image-Based RenderingA Brief Overview

David Luebke

University of Virginia

Page 2: Image-Based Rendering A Brief Overview David Luebke University of Virginia.

Context

Bad: I don’t have assignment #1 graded– Worse: won’t be graded this week at all

Next major topic: programming the vertex and fragment pipelines– Big topic, several lectures

– Assignment #3 But first, next couple of lectures will be

“culture” topics– Image-based rendering

– Parallel graphics

Page 3: Image-Based Rendering A Brief Overview David Luebke University of Virginia.

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

Page 4: Image-Based Rendering A Brief Overview David Luebke University of Virginia.

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

Page 5: Image-Based Rendering A Brief Overview David Luebke University of Virginia.

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

Page 6: Image-Based Rendering A Brief Overview David Luebke University of Virginia.

Depth per pixel

What if we could assign an exact depth to every pixel?

Ex: MIT Image-Based Editing system

Page 7: Image-Based Rendering A Brief Overview David Luebke University of Virginia.

Depth per pixel continued

What if we had a “camera” that automatically acquired depth at every pixel?

Ex: deltasphere Ex: Monticello project

Page 8: Image-Based Rendering A Brief Overview David Luebke University of Virginia.

General image-based rendering

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

rendering

Page 9: Image-Based Rendering A Brief Overview David Luebke University of Virginia.

A 4-D Light Field

Page 10: Image-Based Rendering A Brief Overview David Luebke University of Virginia.

Creating Light Fields

Page 11: Image-Based Rendering A Brief Overview David Luebke University of Virginia.

Light Field as anArray of Images

Page 12: Image-Based Rendering A Brief Overview David Luebke University of Virginia.

Fast Rendering of Light Fields

Page 13: Image-Based Rendering A Brief Overview David Luebke University of Virginia.

Use Gouraud Shading Hardware!

Page 14: Image-Based Rendering A Brief Overview David Luebke University of Virginia.

Light Field Rendering

Demo of Stanford viewer and light fields…

Page 15: Image-Based Rendering A Brief Overview David Luebke University of Virginia.

View-Dependent Rendering

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:

http://graphics.stanford.edu/~kapu/vbr/webslides/index.html