Three-Dimensional Surface Relief Completion Via Nonparametric Techniques

Authors:
Toby P. Breckon;Robert B. Fisher
Affiliations:
Cranfield University, Bedford;University of Edinburgh, Edinburgh
Venue:
IEEE Transactions on Pattern Analysis and Machine Intelligence
Year:
2008

Citing 0
Cited 5

Hole filling in 3D volumetric objects

Pattern Recognition
A hierarchical extension to 3D non-parametric surface relief completion

Pattern Recognition
3D shape restoration via matrix recovery

ACCV'10 Proceedings of the 2010 international conference on Computer vision - Volume part II
Technical Section: Automatic hole-filling of CAD models with feature-preserving

Computers and Graphics
Preserving the Khmer smile: classifying and restoring the faces of Bayon

VAST'11 Proceedings of the 12th International conference on Virtual Reality, Archaeology and Cultural Heritage

Quantified Score

Hi-index	0.14

Visualization

Abstract

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.