Variational Image Motion Computation: Theoretical Framework, Problems and Perspectives

Christoph Schnörr, Joachim WeickertDAGM-Symposium 2000 · OpenReview

Abstract

Many differential methods for the recovery of the optic flow field from an image sequence can be expressed in terms of a variational problem where the optic flow minimizes some energy. Typically, these energy functionals consist of two terms: a data term, which requires e.g. that a brightness constancy assumption holds, and a regularizer that encourages global or piecewise smoothness of the flow field. In this paper we present a systematic Classification of rotation invariant convex regularizers by exploring their connection to diffusion filters for multichannel images. This taxonomy provides a unifying framework for data-driven and flow-driven, isotropic and anisotropic, as well as spatial and spatiotemporal regularizers. While some of these techniques are classic methods from the literature, others are derived here for the first time. We conclude by pointing out some important research issues related to variational optic flow computation.
BibTeX
@inproceedings{schnorr2000variational,
  author = {Christoph Schnörr and Joachim Weickert},
  title = {{Variational Image Motion Computation: Theoretical Framework, Problems and Perspectives}},
  booktitle = {DAGM-Symposium},
  year = {2000},
  url = {https://openreview.net/forum?id=ffslJ90MsV5},
}

Loading related content...

Figure