Subspace Video Stabilization
ACM Transcations on Graphics, Volume 30, Number 1, page 1--10 — 2011
We present a robust and efficient approach to video stabilization that
achieves high-quality camera motion for a wide range of videos. In this
paper, we focus on the problem of transforming a set of input 2D motion
trajectories so that they are both smooth and resemble visually plausible
views of the imaged scene; our key insight is that we can achieve this goal
by enforcing subspace constraints on feature trajectories while smoothing
them. Our approach assembles tracked features in the video into a trajectory
matrix, factors it into two low-rank matrices, and performs filtering
or curve fitting in a low-dimensional linear space. In order to process long
videos, we propose a moving factorization that is both efficient and streamable.
Our experiments confirm that our approach can efficiently provide stabilization
results comparable with prior 3D methods in cases where those
methods succeed, but also provides smooth camera motions in cases where
such approaches often fail, such as videos that lack parallax. The presented
approach offers the first method that both achieves high-quality video stabilization
and is practical enough for consumer applications.
Images and movies
BibTex references
@Article{LGWJA11, author = "Liu, Feng and Gleicher, Michael and Wang, Jue and Jin, Hailin and Agarwala, Aseem", title = "Subspace Video Stabilization", journal = "ACM Transcations on Graphics", number = "1", volume = "30", pages = "1--10", year = "2011", ee = "http://portal.acm.org/citation.cfm?id=1899408", projecturl = "http://www.cs.pdx.edu/~fliu/project/subspace_stabilization/", url = "http://graphics.cs.wisc.edu/Papers/2011/LGWJA11" }