Supplementary Material Page

Modeling Temporal Coherence for Optical Flow

ICCV 2011

Sebastian Volz¹       Andrés Bruhn¹       Levi Valgaerts¹       Henning Zimmer<sup>2

1</sup>Vision and Image Processing Group,
Saarland University, Campus E 1.1, Saarbrücken, Germany
{bruhn, volz} @mmci.uni-saarland.de

²Mathematical Image Analysis Group,
Saarland University, Campus E1.1, Saarbrücken, Germany
{valgaerts, zimmer} @mia.uni-saarland.de

Abstract
Despite the fact that temporal coherence is undeniably one of the key aspects when processing video data, this concept has hardly been exploited in recent optical flow methods. In this paper, we will present a novel parametrization for multi-frame optical flow computation that naturally enables us to embed the assumption of a temporally coherent spatial flow structure, as well as the assumption that the optical flow is smooth along motion trajectories. While the first assumption is realized by expanding spatial regularization over multiple frames, the second assumption is imposed by two novel first- and second-order trajectorial smoothness terms. With respect to the latter, we investigate an adaptive decision scheme that makes a local (per pixel) or global (per sequence) selection of the most appropriate model possible. Experiments show the clear superiority of our approach when compared to existing strategies for imposing temporal coherence. Moreover, we demonstrate the state-of-the-art performance of our method by achieving Top 3 results at the widely used Middlebury benchmark.

This is a supplementary material page for the paper Modeling Temporal Coherence for Optical Flow that has been published at the 13th IEEE International Conference on Computer Vision (6-13 Nov. 2011, Barcelona, Spain).

Downloads

• Supplementary Material [pdf, 14.4MB]
• Supplementary Video [zipped avi, 11MB]
• Bibtex

Additional Information

• Additional Experimental Results