English

Convective regularization for optical flow

Optimization and Control 2021-06-09 v2 Computer Vision and Pattern Recognition

Abstract

We argue that the time derivative in a fixed coordinate frame may not be the most appropriate measure of time regularity of an optical flow field. Instead, for a given velocity field vv we consider the convective acceleration vt+vvv_t + \nabla v v which describes the acceleration of objects moving according to vv. Consequently we investigate the suitability of the nonconvex functional vt+vvL22\|v_t + \nabla v v\|^2_{L^2} as a regularization term for optical flow. We demonstrate that this term acts as both a spatial and a temporal regularizer and has an intrinsic edge-preserving property. We incorporate it into a contrast invariant and time-regularized variant of the Horn-Schunck functional, prove existence of minimizers and verify experimentally that it addresses some of the problems of basic quadratic models. For the minimization we use an iterative scheme that approximates the original nonlinear problem with a sequence of linear ones. We believe that the convective acceleration may be gainfully introduced in a variety of optical flow models.

Keywords

Cite

@article{arxiv.1505.04938,
  title  = {Convective regularization for optical flow},
  author = {José A. Iglesias and Clemens Kirisits},
  journal= {arXiv preprint arXiv:1505.04938},
  year   = {2021}
}
R2 v1 2026-06-22T09:37:00.411Z