A Highly Efficient GPU Implementation for Variational Optic Flow Based on the Euler-Lagrange Framework
Abstract
The Euler-Lagrange (EL) framework is the most widely-used strategy for solving variational optic flow methods. We present the first approach that solves the EL equations of state-of-the-art methods on sequences with $640 \!\times\! 480$ pixels in near-realtime on GPUs. This performance is achieved by combining two ideas: (i) We extend the recently proposed Fast Explicit Diffusion (FED) scheme to optic flow, and additionally embed it into a coarse-to-fine strategy. (ii) We parallelise our complete algorithm on a GPU, where a careful optimisation of global memory operations and an efficient use of on-chip memory guarantee a good performance. Applying our approach to the variational ‘Complementary Optic Flow’ method (Zimmer et al. (2009)), we obtain highly accurate flow fields in less than a second. This currently constitutes the fastest method in the top 10 of the widely used Middlebury benchmark.
Cite
Text
Gwosdek et al. "A Highly Efficient GPU Implementation for Variational Optic Flow Based on the Euler-Lagrange Framework." European Conference on Computer Vision Workshops, 2010. doi:10.1007/978-3-642-35740-4_29Markdown
[Gwosdek et al. "A Highly Efficient GPU Implementation for Variational Optic Flow Based on the Euler-Lagrange Framework." European Conference on Computer Vision Workshops, 2010.](https://mlanthology.org/eccvw/2010/gwosdek2010eccvw-highly/) doi:10.1007/978-3-642-35740-4_29BibTeX
@inproceedings{gwosdek2010eccvw-highly,
title = {{A Highly Efficient GPU Implementation for Variational Optic Flow Based on the Euler-Lagrange Framework}},
author = {Gwosdek, Pascal and Zimmer, Henning and Grewenig, Sven and Bruhn, Andrés and Weickert, Joachim},
booktitle = {European Conference on Computer Vision Workshops},
year = {2010},
pages = {372-383},
doi = {10.1007/978-3-642-35740-4_29},
url = {https://mlanthology.org/eccvw/2010/gwosdek2010eccvw-highly/}
}