Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
533439 | Pattern Recognition | 2012 | 14 Pages |
Typical stereo and laser scan based 3D acquisition approaches are essentially limited to 2.5D capture. The resulting 3D completion problem, to derive missing information in 2.5D scenes from limited contextual information, has received increasing attention in literature. Here we propose a hierarchical extension to our recent non-parametric approach for the 3D completion of surface relief detail to allow the resolution of inconsistencies arising in the global structure of an area completed with this technique. We test our approach over a range of surface types and contrast the presence of global discontinuities in the resulting completion with those of the earlier approach.
► We investigate a multi-scale approach to 3D surface relief completion. ► Extends prior work that used a mono-scale approach. ► We propose a multi-scale technique and validate over exemplar 3D surfaces. ► This approach maintains global surface structure where the mono-scale approach fails. ► Succeeds in irregular relief completion and achieves significant computational gain.