A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms

  • Authors:
  • D. Scharstein;R. Szeliski;R. Zabih

  • Affiliations:
  • -;-;-

  • Venue:
  • SMBV '01 Proceedings of the IEEE Workshop on Stereo and Multi-Baseline Vision (SMBV'01)
  • Year:
  • 2001

Quantified Score

Hi-index 0.00

Visualization

Abstract

Stereo matching is one of the most active research areasin computer vision. While a large number of algorithmsfor stereo correspondence have been developed, relativelylittle work has been done on characterizing their performance. In this paper, we present a taxonomy of dense, two-frame stereo methods designed to assess the different components and design decisions made in individual stereo algorithms. Using this taxonomy, we compare existing stereomethods and present experiments evaluating the performance of many different variants. In order to establish acommon software platform and a collection of data sets foreasy evaluation, we have designed a stand-alone, flexibleC++ implementation that enables the evaluation of individual components and that can be easily extended to includenew algorithms. We have also produced several new multi-frame stereo data sets with ground truth, and are makingboth the code and data sets available on the Web .