An introduction to image-based rendering

  • Authors:
  • Heung Yeung Shum;Yin Li;Sing Bing Kang

  • Affiliations:
  • Microsoft Research Asia, Beijing, P.R. China;Hong Kong University of Science and Technology;Microsoft Research Asia, Beijing, P.R. China

  • Venue:
  • Integrated image and graphics technologies
  • Year:
  • 2004

Quantified Score

Hi-index 0.00

Visualization

Abstract

In this chapter, we review the techniques for image-based rendering. Unlike traditional 3D computer graphics in which 3D geometry of the scene is known, image-based rendering (IBR) techniques render novel views directly from input images. IBR techniques can be classified into three categories according to how much geometric information is used: rendering without geometry, rendering with implicit geometry (i.e., correspondence), and rendering with explicit geometry (either with approximate or accurate geometry). We discuss the characteristics of these categories and their representative techniques.IBR techniques demonstrate a surprising diverse range in their extent of use of images and geometry in representing 3D scenes. We explore the issues in trading off the use of images and geometry by revisiting plenoptic sampling analysis and the notions of view dependency and geometric proxies. Finally, we highlight a practical IBR technique called pop-up light field. It models a sparse light field using a set of coherent layers, which incorporates both color and matting information, and renders in real time and free of aliasing.