Solving Dense Image Matching in Real-Time using Discrete-Continuous Optimization

Oleksandr Shekhovtsov, Christian Reinbacher, Gottfried Graber, Thomas Pock

Research output: Contribution to conferencePaperpeer-review

Abstract

Dense image matching is a fundamental low-level problem in Computer Vision, which has received tremendous attention from both discrete and continuous optimization communities. The goal of this paper is to combine the advantages of discrete and continuous optimization in a coherent framework. We devise a model based on energy minimization, to be optimized by both discrete and continuous algorithms in a consistent way. In the discrete setting, we propose a novel optimization algorithm that can be massively parallelized. In the continuous setting we tackle the problem of non-convex regularizers by a formulation based on differences of convex functions. The resulting hybrid discrete-continuous algorithm can be efficiently accelerated by modern GPUs and we demonstrate its real-time performance for the applications of dense stereo matching and optical flow.
Original languageEnglish
Number of pages13
Publication statusPublished - 23 Jan 2016
EventComputer Vision Winter Workshop: CVWW 2016 - Rimske Toplice, Slovenia
Duration: 3 Feb 20165 Feb 2016

Workshop

WorkshopComputer Vision Winter Workshop
Abbreviated titleCVWW 2016
Country/TerritorySlovenia
CityRimske Toplice
Period3/02/165/02/16

Keywords

  • cs.CV

Fingerprint

Dive into the research topics of 'Solving Dense Image Matching in Real-Time using Discrete-Continuous Optimization'. Together they form a unique fingerprint.

Cite this