Three-Dimensional Surface Relief Completion Via Nonparametric Techniques

Toby P. Breckon, Robert B. Fisher

Research output: Contribution to journalArticlepeer-review

Abstract / Description of output

Common 3D acquisition techniques, such as laser scanning and stereo capture, are realistically only 2.5D in nature. Here we consider the automated completion of hidden or missing portions in 3D scenes originally acquired from 2.5D (or 3D) capture. We propose an approach based on the non-parametric propagation of available scene knowledge from the known (visible) scene areas to these unknown (invisible) 3D regions in conjunction with an initial underlying geometric surface completion.
Original languageEnglish
Pages (from-to)2249-2255
Number of pages7
JournalIEEE Transactions on Pattern Analysis and Machine Intelligence
Volume30
Issue number12
DOIs
Publication statusPublished - Dec 2008

Keywords / Materials (for Non-textual outputs)

  • Computational Geometry and Object Modeling
  • Computer Graphics
  • Computer Vision
  • Image Processing and Computer Vision
  • Range Data
  • Shape
  • Surface Fitting

Fingerprint

Dive into the research topics of 'Three-Dimensional Surface Relief Completion Via Nonparametric Techniques'. Together they form a unique fingerprint.

Cite this