Abstract
Videos acquired in low-light conditions often exhibit motion blur,
which depends on the motion of the objects relative to the camera. This is not only
visually unpleasing, but can hamper further processing. With this paper we are the
first to show how the availability of stereo video can aid the challenging video de-
blurring task. We leverage 3D scene flow, which can be estimated robustly even
under adverse conditions. We go beyond simply determining the object motion in
two ways: First, we show how a piecewise rigid 3D scene flow representation al-
lows to induce accurate blur kernels via local homographies. Second, we exploit
the estimated motion boundaries of the 3D scene flow to mitigate ringing arti-
facts using an iterative weighting scheme. Being aware of 3D object motion, our
approach can deal robustly with an arbitrary number of independently moving
objects. We demonstrate its benefit over state-of-the-art video deblurring using
quantitative and qualitative experiments on rendered scenes and real videos.
Article
Research in this project by Anita Sellent (TU Darmstadt and TU Dresden), Carsten Rother (TU Dresden) and Stefan Roth (TU Darmstadt) will be published on ECCV 2016 in Amsterdam.
[preprint] [supplement] [poster] [video]
Downloads
[code] [synthetic datasets] [motorized rail datasets]