Efficient minimal-surface regularization of perspective depth maps in variational stereo
| Autor: | Stefano Soatto, Gottfried Graber, Jonathan Balzer, Thomas Pock |
|---|---|
| Rok vydání: | 2015 |
| Předmět: |
Minimal surface
business.industry Computation media_common.quotation_subject Reconstruction algorithm Ambiguity Surface (topology) Regularization (mathematics) Computer vision Artificial intelligence business Algorithm Surface reconstruction ComputingMethodologies_COMPUTERGRAPHICS Mathematics media_common |
| Zdroj: | CVPR |
| DOI: | 10.1109/cvpr.2015.7298649 |
| Popis: | 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 depth-map-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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|