Image-based rendering

Sing Bing Kang*, Yin Li, Xin Tong, Heung Yeung Shum

*Corresponding author for this work

Research output: Contribution to journalJournal Articlepeer-review

24 Citations (Scopus)

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.

Original languageEnglish
Pages (from-to)173-258
Number of pages86
JournalFoundations and Trends in Computer Graphics and Vision
Volume2
Issue number3
DOIs
Publication statusPublished - 2006
Externally publishedYes

Fingerprint

Dive into the research topics of 'Image-based rendering'. Together they form a unique fingerprint.

Cite this