Inproceedings,

Order-adaptive Regularisation for Variational Optical Flow: Global, Local and in Between.

, , and .
Scale Space and Variational Methods in Computer Vision. SSVM 2017. Lecture Notes in Computer Science, 10302, page 550-562. Springer International Publishing, (2017)
DOI: 10.1007/978-3-319-58771-4_44

Abstract

Recent approaches for variational motion estimation typically either rely on first or second order regularisation strategies. While first order strategies are more appropriate for scenes with fronto-parallel motion, second order constraints are superior if it comes to the estimation of affine flow fields. Since using the wrong regularisation order may lead to a significant deterioration of the results, it is surprising that there has not been much effort in the literature so far to determine this order automatically. In our work, we address the aforementioned problem in two ways. (i) First, we discuss two anisotropic smoothness terms of first and second order, respectively, that share important structural properties and that are thus particularly suited for being combined within an order-adaptive variational framework. (ii) Secondly, based on these two smoothness terms, we develop four different variational methods and with it four different strategies for adaptively selecting the regularisation order: a global and a local strategy based on half-quadratic regularisation, a non-local approach that relies on neighbourhood information, and a region based method using level sets. Experiments on recent benchmarks show the benefits of each of the strategies. Moreover, they demonstrate that adaptively combining different regularisation orders not only allows to outperform single-order strategies but also to obtain advantages beyond the ones of a frame-wise selection.

Tags

Users

  • @hlawatml
  • @sfbtrr161
  • @mueller
  • @leonkokkoliadis
  • @dblp
  • @tinabarthelmes
  • @visus

Comments and Reviews