Soft Cost Aggregation with Multi-resolution Fusion

  • Xiao Tan
  • Changming Sun
  • Dadong Wang
  • Yi Guo
  • Tuan D. Pham
Conference paper

DOI: 10.1007/978-3-319-10602-1_2

Part of the Lecture Notes in Computer Science book series (LNCS, volume 8693)
Cite this paper as:
Tan X., Sun C., Wang D., Guo Y., Pham T.D. (2014) Soft Cost Aggregation with Multi-resolution Fusion. In: Fleet D., Pajdla T., Schiele B., Tuytelaars T. (eds) Computer Vision – ECCV 2014. ECCV 2014. Lecture Notes in Computer Science, vol 8693. Springer, Cham

Abstract

This paper presents a simple and effective cost volume aggregation framework for addressing pixels labeling problem. Our idea is based on the observation that incorrect labelings are greatly reduced in cost volume aggregation results from low resolutions. However, image details may be lost in the low resolution results. To take advantage of the results from low resolution for reducing these incorrect labelings while preserving details, we propose a multi-resolution cost aggregation method (MultiAgg) by using a soft fusion scheme based on min-convolution. We implement our MultiAgg in applications on stereo matching and interactive image segmentation. Experimental results show that our method significantly outperforms conventional cost aggregation methods in labeling accuracy. Moreover, although MultiAgg is a simple and straight-forward method, it produces results which are close to or even better than those from iterative methods based on global optimization.

Keywords

Multi-resolution fusion Cost aggregation Stereo matching Interactive segmentation 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Xiao Tan
    • 1
    • 2
  • Changming Sun
    • 1
  • Dadong Wang
    • 1
  • Yi Guo
    • 1
  • Tuan D. Pham
    • 3
  1. 1.CSIRO Computational InformaticsNorth RydeAustralia
  2. 2.The University of New South WalesCanberraAustralia
  3. 3.The University of AizuFukushimaJapan

Personalised recommendations