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
Hi-index | 0.14 |
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.