Sublabel-Accurate Discretization of Nonconvex Free-Discontinuity Problems
Moellenhoff T, Cremers D (2017)
Publication Type: Conference contribution
Publication year: 2017
Publisher: Institute of Electrical and Electronics Engineers Inc.
Book Volume: 2017-October
Pages Range: 1192-1200
Conference Proceedings Title: Proceedings of the IEEE International Conference on Computer Vision
Event location: Venice, ITA
ISBN: 9781538610329
Abstract
In this work we show how sublabel-accurate multilabeling approaches [15, 18] can be derived by approximating a classical label-continuous convex relaxation of nonconvex free-discontinuity problems. This insight allows to extend these sublabel-accurate approaches from total variation to general convex and nonconvex regularizations. Furthermore, it leads to a systematic approach to the discretization of continuous convex relaxations. We study the relationship to existing discretizations and to discrete-continuous MRFs. Finally, we apply the proposed approach to obtain a sublabel-accurate and convex solution to the vectorial Mumford-Shah functional and show in several experiments that it leads to more precise solutions using fewer labels.
Involved external institutions
Germany (DE)How to cite
APA:
Moellenhoff, T., & Cremers, D. (2017). Sublabel-Accurate Discretization of Nonconvex Free-Discontinuity Problems. In Proceedings of the IEEE International Conference on Computer Vision (pp. 1192-1200). Venice, ITA: Institute of Electrical and Electronics Engineers Inc..
MLA:
Moellenhoff, Thomas, and Daniel Cremers. "Sublabel-Accurate Discretization of Nonconvex Free-Discontinuity Problems." Proceedings of the 16th IEEE International Conference on Computer Vision, ICCV 2017, Venice, ITA Institute of Electrical and Electronics Engineers Inc., 2017. 1192-1200.
BibTeX: Download