Sublabel-Accurate Convex Relaxation of Vectorial Multilabel Energies

Emanuel Laude, Thomas Möllenhoff, Michael Moeller, Jan Lellmann, Daniel Cremers


Convex relaxations of multilabel problems have been demonstrated to produce provably optimal or near-optimal solutions to a variety of computer vision problems. Yet, they are of limited practical use as they require a fine discretization of the label space, entailing a huge demand in memory and runtime. In this work, we propose the first sublabel accurate convex relaxation for vectorial multilabel problems. Our key idea is to approximate the dataterm in a piecewise convex (rather than piecewise linear) manner. As a result we have a more faithful approximation of the original cost function that provides a meaningful interpretation for fractional solutions of the relaxed convex problem.
Original languageEnglish
Title of host publicationComputer Vision – ECCV 2016
EditorsBastian Leibe, Jiri Matas, Nicu Sebe, Max Welling
Number of pages14
PublisherSpringer International Publishing
Publication date17.09.2016
ISBN (Print)978-3-319-46447-3
ISBN (Electronic)978-3-319-46448-0
Publication statusPublished - 17.09.2016
Event14th European Conference on Computer Vision - Amsterdam, Netherlands
Duration: 11.10.201614.10.2016
Conference number: Part I


Dive into the research topics of 'Sublabel-Accurate Convex Relaxation of Vectorial Multilabel Energies'. Together they form a unique fingerprint.

Cite this