|
Image-Based Rendering
Foundations and Trends® in
Computer Graphics and Vision
Volume 2 Issue 3
DOI: 10.1561/0600000012
Image-Based Rendering
Sing Bing Kang
Microsoft Research, USA, sbkang@microsoft.com
Yin Li
Microsoft Corporation, USA, yl@microsoft.com
Xin Tong
Microsoft Research Asia, China, xtong@microsoft.com
Heung-Yeung Shum
Microsoft Research Asia, China, hshum@microsoft.com
Abstract
Image-based rendering (IBR) is unique in that it requires computer graphics, computer vision, and image processing to join
forces to solve a common goal, namely photorealistic rendering through the use of images. IBR as an area of research has been
around for about ten years, and substantial progress has been achieved in effectively capturing, representing, and rendering
scenes. In this article, we survey the techniques used in IBR. Our survey shows that representations and rendering techniques
can differ radically, depending on design decisions related to ease of capture, use of geometry, accuracy of geometry (if
used), number and distribution of source images, degrees of freedom for virtual navigation, and expected scene complexity.
|