Abstract
We propose a method for dense three-dimensional surface reconstruction that leverages the strengths of shape-based approaches, by imposing regularization that respects
the geometry of the surface, and the strength of depthmap-based stereo, by avoiding costly computation of surface topology. The result is a near real-time variational reconstruction algorithm free of the staircasing artifacts that affect depth-map and plane-sweeping approaches. This is made possible by exploiting the gauge ambiguity to design
a novel representation of the regularizer that is linear in the parameters and hence amenable to be optimized with state-of-the-art primal-dual numerical schemes.
the geometry of the surface, and the strength of depthmap-based stereo, by avoiding costly computation of surface topology. The result is a near real-time variational reconstruction algorithm free of the staircasing artifacts that affect depth-map and plane-sweeping approaches. This is made possible by exploiting the gauge ambiguity to design
a novel representation of the regularizer that is linear in the parameters and hence amenable to be optimized with state-of-the-art primal-dual numerical schemes.
| Original language | English |
|---|---|
| Title of host publication | The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) |
| Publisher | . |
| Pages | 511-520 |
| Publication status | Published - 2015 |
| Event | 2015 IEEE Conference on Computer Vision and Pattern Recognition: CVPR 2015 - Boston, United States Duration: 7 Jun 2015 → 12 Jun 2015 |
Conference
| Conference | 2015 IEEE Conference on Computer Vision and Pattern Recognition |
|---|---|
| Abbreviated title | CVPR 2015 |
| Country/Territory | United States |
| City | Boston |
| Period | 7/06/15 → 12/06/15 |
Fields of Expertise
- Information, Communication & Computing
Treatment code (Nähere Zuordnung)
- Application