Novel view synthesis by cascading trilinear tensors

Shai Avidan*, Amnon Shashua

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

Abstract

We present a new method for synthesizing novel views of a 3D scene from two or three reference images in full correspondence. The core of this work is the use and manipulation of an algebraic entity termed the trilinear fensorthat links point correspondences across three images. For a given virtual camera position and orientation a new trilinear tensor can be computed based on the original tensor of the reference images. The desired view can then be created using this new trilinear tensor and point correspondences across two of the reference images.

Original languageEnglish
Pages (from-to)293-306
Number of pages14
JournalIEEE Transactions on Visualization and Computer Graphics
Volume4
Issue number4
DOIs
StatePublished - 1998
Externally publishedYes

Keywords

  • Image manipulation
  • Image-based rendering
  • Trilinear tensor
  • Virtual reality

Fingerprint

Dive into the research topics of 'Novel view synthesis by cascading trilinear tensors'. Together they form a unique fingerprint.

Cite this