DMCA
Motion Detail Preserving Optical Flow Estimation
Cached
Download Links
| Citations: | 72 - 1 self |
BibTeX
@MISC{Xu_motiondetail,
author = {Li Xu and Jiaya Jia and Yasuyuki Matsushita},
title = {Motion Detail Preserving Optical Flow Estimation },
year = {}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
We discuss the cause of a severe optical flow estimation problem that fine motion structures cannot always be correctly reconstructed in the commonly employed multiscale variational framework. Our major finding is that significant and abrupt displacement transition wrecks small-scale motion structures in the coarse-to-fine refinement. A novel optical flow estimation method is proposed in this paper to address this issue, which reduces the reliance of the flow estimates on their initial values propagated from the coarser level and enables recovering many motion details in each scale. The contribution of this paper also includes adaption of the objective function and development of a new optimization procedure. The effectiveness of our method is borne out by experiments for both large- and small-displacement optical flow estimation.
Keyphrases
new optimization procedure major finding coarse-to-fine refinement severe optical flow estimation problem flow estimate coarser level initial value multiscale variational framework small-displacement optical flow estimation small-scale motion structure many motion detail novel optical flow estimation method fine motion structure abrupt displacement transition objective function
