Sublabel-Accurate Discretization of Nonconvex Free-Discontinuity Problems

Thomas Mollenhoff, Daniel Cremers

Publikation: Beitrag in Buch/Bericht/KonferenzbandKonferenzbeitragBegutachtung

17 Zitate (Scopus)

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.

OriginalspracheEnglisch
TitelProceedings - 2017 IEEE International Conference on Computer Vision, ICCV 2017
Herausgeber (Verlag)Institute of Electrical and Electronics Engineers Inc.
Seiten1192-1200
Seitenumfang9
ISBN (elektronisch)9781538610329
DOIs
PublikationsstatusVeröffentlicht - 22 Dez. 2017
Veranstaltung16th IEEE International Conference on Computer Vision, ICCV 2017 - Venice, Italien
Dauer: 22 Okt. 201729 Okt. 2017

Publikationsreihe

NameProceedings of the IEEE International Conference on Computer Vision
Band2017-October
ISSN (Print)1550-5499

Konferenz

Konferenz16th IEEE International Conference on Computer Vision, ICCV 2017
Land/GebietItalien
OrtVenice
Zeitraum22/10/1729/10/17

Fingerprint

Untersuchen Sie die Forschungsthemen von „Sublabel-Accurate Discretization of Nonconvex Free-Discontinuity Problems“. Zusammen bilden sie einen einzigartigen Fingerprint.

Dieses zitieren