Human trajectory prediction via neural social physics

J Yue, D Manocha, H Wang - European conference on computer vision, 2022 - Springer
Trajectory prediction has been widely pursued in many fields, and many model-based and
model-free methods have been explored. The former include rule-based, geometric or …

Optical flow modeling and computation: A survey

D Fortun, P Bouthemy, C Kervrann - Computer Vision and Image …, 2015 - Elsevier
Optical flow estimation is one of the oldest and still most active research domains in
computer vision. In 35 years, many methodological concepts have been introduced and …

High accuracy optical flow estimation based on a theory for warping

T Brox, A Bruhn, N Papenberg, J Weickert - Computer Vision-ECCV 2004 …, 2004 - Springer
We study an energy functional for computing optical flow that combines three assumptions: a
brightness constancy assumption, a gradient constancy assumption, and a discontinuity …

Lucas/Kanade meets Horn/Schunck: Combining local and global optic flow methods

A Bruhn, J Weickert, C Schnörr - International journal of computer vision, 2005 - Springer
Differential methods belong to the most widely used techniques for optic flow computation in
image sequences. They can be classified into local methods such as the Lucas–Kanade …

Motion detail preserving optical flow estimation

L Xu, J Jia, Y Matsushita - IEEE Transactions on Pattern …, 2011 - ieeexplore.ieee.org
A common problem of optical flow estimation in the multiscale variational framework is that
fine motion structures cannot always be correctly estimated, especially for regions with …

Highly accurate optic flow computation with theoretically justified warping

N Papenberg, A Bruhn, T Brox, S Didas… - International Journal of …, 2006 - Springer
In this paper, we suggest a variational model for optic flow computation based on non-
linearised and higher order constancy assumptions. Besides the common grey value …

Optic flow in harmony

H Zimmer, A Bruhn, J Weickert - International Journal of Computer Vision, 2011 - Springer
Most variational optic flow approaches just consist of three constituents: a data term, a
smoothness term and a smoothness weight. In this paper, we present an approach that …

Reliable estimation of dense optical flow fields with large displacements

L Alvarez, J Weickert, J Sánchez - International Journal of Computer Vision, 2000 - Springer
In this paper we show that a classic optical flow technique by Nagel and Enkelmann (1986,
IEEE Trans. Pattern Anal. Mach. Intell., Vol. 8, pp. 565–593) can be regarded as an early …

A theoretical framework for convex regularizers in PDE-based computation of image motion

J Weickert, C Schnörr - International Journal of Computer Vision, 2001 - Springer
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 …

Variational optic flow computation with a spatio-temporal smoothness constraint

J Weickert, C Schnörr - Journal of mathematical imaging and vision, 2001 - Springer
Nonquadratic variational regularization is a well-known and powerful approach for the
discontinuity-preserving computation of optic flow. In the present paper, we consider an …