Max-Planck-Institut für Informatik
max planck institut
informatik
mpii logo Minerva of the Max Planck Society
 

MPI-INF or MPI-SWS or Local Campus Event Calendar

<< Previous Entry Next Entry >> New Event Entry Edit this Entry Login to DB (to update, delete)
What and Who
Title:Sublabel Accurate Relaxation of Nonconvex Energies arising in Computer Vision Problems
Speaker:Emanuel Laude
coming from:TU Munich
Speakers Bio:
Event Type:Talk
Visibility:D2, D4, MMCI
We use this to send out email in the morning.
Level:AG Audience
Language:English
Date, Time and Location
Date:Tuesday, 12 July 2016
Time:14:00
Duration:45 Minutes
Location:Saarbrücken
Building:E1 4
Room:633
Abstract
We propose a novel spatially continuous framework for convex relaxations based on functional lifting. Our method can be interpreted as a sublabel-accurate solution to multilabel problems. We show that previously proposed functional lifting methods optimize an energy which is linear between two labels and hence require (often infinitely) many labels for a faithful approximation. In contrast, the proposed formulation is based on a piecewise convex approximation and therefore needs far fewer labels. In comparison to recent MRF-based approaches, our method is formulated in a spatially continuous setting and shows less grid bias. Moreover, in a local sense, our formulation is the tightest possible convex relaxation. It is easy to implement and allows an efficient primal-dual optimization on GPUs. We show the effectiveness of our approach on several computer vision problems.
Contact
Name(s):Björn Andres
EMail:andres@mpi-inf.mpg.de
Video Broadcast
Video Broadcast:NoTo Location:
Tags, Category, Keywords and additional notes
Keywords:convex optimization; computer vision
Note:
Attachments, File(s):
Created by:Björn Andres, 06/09/2016 10:49 AMLast modified by:Uwe Brahm/MPII/DE, 11/24/2016 04:13 PM
  • Björn Andres, 06/09/2016 10:49 AM -- Created document.