Computer Graphics
TU Braunschweig

A Loop-Consistency Measure for Dense Correspondences in Multi-View Video

A Loop-Consistency Measure for Dense Correspondences in Multi-View Video

Many applications in computer vision and computer graphics require dense correspondences between images of multi-view video streams. Most state-of-the-art algorithms estimate correspondences by considering pairs of images. However, in multi-view videos, several images capture nearly the same scene. In this article we show that this redundancy can be exploited to estimate more robust and consistent correspondence fields. We use the multi-video data structure to establish a confidence measure based on the consistency of the correspondences in a loop of three images. This confidence measure can be applied after flow estimation is terminated to find the pixels for which the estimate is reliable. However, including the measure directly into the estimation process yields dense and highly accurate correspondence fields. Additionally, application of the loop consistency confidence measure allows to include sparse feature matches directly into the dense optical flow estimation. With the confidence measure, spurious matches can be successfully suppressed during optical flow estimation while correct matches contribute to increase the accuracy of the flow.

Author(s):Anita Sellent, Kai Ruhl, Marcus Magnor
Journal:Journal of Image and Vision Computing Vol. 30
Project(s): Image-space Editing of 3D Content  Reality CG 

  title = {A Loop-Consistency Measure for Dense Correspondences in Multi-View Video},
  author = {Sellent, Anita and Ruhl, Kai and Magnor, Marcus},
  journal = {Journal of Image and Vision Computing},
  volume = {30},
  number = {9},
  pages = {641--654},
  month = {Jun},
  year = {2012}